01Safety
0.0 / 30
What changed in the harness
Selection accuracy 76→83, token cost up 6%, unconfirmed writes 0%→0%.
Category breakdown
Where the score comes from.
Earned points across the four signals Gradable measures. Safety and Legibility are scored out of 30; Economics and Discoverability are scored out of 20.
02Legibility
24.4 / 30
03Economics
19.9 / 20
04Discoverability
9.8 / 20
Highest-impact fix
Estimated gain +30 pointsAdd explicit identity and permission preflight tools
Expose machine-readable principal/tenant confirmation and a non-mutating permission check so agents can verify both before destructive actions.
Description evidence
Defects and rewrites.
5 defects found across the exposed tool descriptions. Suggested rewrites make purpose, inputs, boundaries, and returns easier for an agent to understand.
| Tool | Defect types | Suggested rewrite |
|---|---|---|
analyze_files |
no_return_description |
Delegate file analysis to the Antigravity CLI (Gemini) instead of reading files yourself. USE THIS whenever a file is large (>200 lines) or the task spans more than 3 files: logs, database dumps, generated code, cross-file reviews, comparisons. The files never enter your context — only the answer does. Returns Gemini's written analysis answering the question, plus a session_id you can pass to follow_up for follow-up questions. |
deep_search |
no_return_description |
Delegate codebase archaeology to the Antigravity CLI: git log/diff/blame spelunking, wide greps across a repo, 'when/why did X change', 'where is Y used'. USE THIS instead of running many search commands yourself — it saves your context. Returns a written summary of what was found, plus a session_id you can pass to follow_up for follow-up questions. |
web_lookup |
no_return_description |
Delegate a web/documentation lookup to the Antigravity CLI (Gemini with web access): library docs, API references, error messages, current versions, external knowledge. USE THIS when you need information you don't have or that may be newer than your training data. Returns a written answer summarizing the web lookup, plus a session_id you can pass to follow_up for follow-up questions. |
adversarial_review |
no_return_description |
Get an adversarial second opinion from a different model family (Gemini Pro). ALWAYS use this for plan critiques, design reviews, and pre-merge code review: it hunts for flaws, edge cases, security issues, and unstated assumptions you may have missed. Returns a written critique describing the issues it found, plus a session_id you can pass to follow_up for follow-up questions. |
delegate |
no_return_description |
Raw delegation to the Antigravity CLI for heavy tasks that don't fit the other tools. agy has full tool access (shell, file reads, web) in the given cwd. Returns agy's final written response to the prompt, plus a session_id you can pass to follow_up for follow-up questions. |
Selection evidence
Confusable tool pairs.
0 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
| No confusable tool pairs were flagged in this assessment. | |||
Compare the field