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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description adds genuinely useful behavior beyond that: exact-match-only semantics (no fuzzy detection), the included spelling variants (Bedrock, Vertex AI, LiteLLM, OpenRouter), and the shape of what comes back.

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 dense sentences with zero filler; the scan scope and match semantics are front-loaded, and the return contents close the statement.

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, the description carries the burden of explaining returns and does so (shutdown date, days left, recommended replacement, source page, file:line). Combined with annotations, an agent has everything needed to call it correctly.

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 description coverage is 100% and the single 'files' parameter is fully documented in the schema, so the description is not required to explain it. It adds no path/content syntax detail beyond the schema, which is the baseline-3 case.

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?

Specific verb (scan) plus resource (source and config files for retired AI model IDs), and it scopes the detection domain to named vendors and hosting platforms. It is clearly distinguishable from siblings like list_model_retirements (which lists) and lookup_model (which looks up one model).

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 the scan-oriented wording, but the description never says when to choose this over siblings such as list_model_retirements or lookup_model, nor does it state prerequisites. The 'exact matches only' note is a scoping constraint rather than a when-to-use rule.

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