01Safety
0.0 / 30
What changed in the harness
Selection accuracy 93→98, token cost up 3%, 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
27.4 / 30
03Economics
20.0 / 20
04Discoverability
9.5 / 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.
2 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 |
|---|---|---|
vibie_create_site |
no_return_description |
Create a NEW Vibie site by uploading a local folder. Use this when the user wants to publish a brand new site, or when no .vibie/site.json marker exists in the folder. Vibie hosts static HTML/CSS/JS at a permanent URL like my-site-a3f9.vibie.page. Auto-creates a .vibie/site.json marker in the folder for future updates. Returns the new site's slug, live URL, name, category, and visibility. |
vibie_update_site |
no_return_description |
Update an existing Vibie site with new content from a local folder. Use this when the user wants to re-deploy or push changes to an already-published site. If .vibie/site.json marker exists in the folder, the slug is read automatically; otherwise pass slug explicitly. Same URL, new content. Returns the updated site's slug, URL, and new last-updated timestamp. |
Selection evidence
Confusable tool pairs.
2 pairs where similar names or overlapping descriptions may send an agent toward the wrong tool.
| Tool A | Tool B | Confidence | Why they collide |
|---|---|---|---|
vibie_create_site |
vibie_update_site |
high | Both take a 'folder' as the primary input and are used for the same conceptual action (publish/deploy a local folder to Vibie). Whether to create vs update hinges on whether a .vibie/site.json marker exists, which the agent may not check before choosing; a task like 'deploy my folder to vibie' or 'push this site live' is genuinely ambiguous without first inspecting the folder for the marker. |
vibie_list_sites |
vibie_get_site |
medium | Both return site metadata (URL, visibility, timestamps). A task like 'what's the URL of my site' or 'check on my site' is ambiguous between listing all sites (if slug unknown) and getting one specific site (if slug known), especially when the agent hasn't yet resolved which slug corresponds to 'my site'. |
Compare the field