Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and non-idempotent, so the safety profile is covered. The description adds real value beyond them: that deletion preserves history (recoverable), and that it auto-acquires the edit lease when no token is supplied — meaningful concurrency behavior not visible elsewhere.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences, front-loaded with the destructive action, then the addressing rule, then the lease caveat. Every clause carries information an agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and only 3 params, the description covers the essential unknowns: deletion semantics (history preserved), file addressing, and lease behavior. It does not describe side effects such as route cleanup for deleted pages or the response shape, a minor residual gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is only 33%, so the description must compensate, and it does: it explains the two addressing modes for the complex `file` anyOf parameter — named files need `type`+`name`, singletons need only `type` — which the schema's anyOf does not articulate. The leaseToken fallback is also explained in-schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Deletes one head file') and clarifies the scope ('head' vs. published), which distinguishes it from websiteSourceCode_published_unpublish and websiteSourceCode_head_restore. The 'preserving history' clause signals the delete is soft, but siblings are not explicitly named.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by 'Deletes one head file', and the leaseToken clause hints at concurrency context. However, it never states when to reach for this versus head_restore, published_unpublish, or files_upsert, and no preconditions or exclusions are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.