01Safety
0.0 / 30
What changed in the harness
Selection accuracy 100→100, token cost up 8%, 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
29.1 / 30
03Economics
20.0 / 20
04Discoverability
12.2 / 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.
3 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 |
|---|---|---|
get_context |
no_return_description |
Retrieves relevant, ranked context from the Project Brain using semantic context selection. Useful when starting a task, resolving design questions, or looking up project standards. Returns a ranked list of matching context entries (e.g. decisions, standards, or notes) with their content and relevance to the given task_hint. |
propose_knowledge |
no_return_description |
Submits a Knowledge Proposal containing newly discovered or updated project design, decisions, schema changes, or API specifications. The proposal enters a validation queue before being compiled into the Project Brain. Returns the created proposal's ID and its current queue/validation status. |
get_history |
no_return_description |
Retrieves version history, diffs, blame, or show details for the Project Brain. Allows reviewing exactly who proposed what, what files changed, what conflicts occurred, and when. Returns action-specific results: a list of version log entries for 'log', full entry details for 'show', a diff between two versions for 'diff', or attribution details (who last changed a given category/title) for 'blame'. |
Selection evidence
Confusable tool pairs.
1 pair where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
get_context |
get_history |
low | Both query the Project Brain, but get_context is for semantic task-relevant lookup while get_history is explicitly for version/diff/blame actions with required enum params, making misselection unlikely for a clear natural-language request. |
Compare the field