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

Annotations already cover the safety profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description is not carrying that burden. It nonetheless adds real behavioral context beyond them: results come from the last saved version, unsaved edits are excluded, and the agent is told to surface the hasDraftChanges warning to the user. It stops short of describing the response shape or ordering of the returned list, which is the remaining gap.

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?

The most important clause, what gets listed and from which version, is front-loaded, and every sentence carries a routing or behavioral instruction. The long parenthetical enumeration of artifact types is dense but earns its place by telling the agent what to expect. Slightly packed, but no wasted wording.

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?

For a two-parameter read tool with full schema coverage and annotations already declaring the safety profile, the description covers scope, sibling routing, and the draft-changes caveat. Since there is no output schema, the description should ideally say more about the shape of the returned list (beyond the hint that it yields 'paths'), which keeps it from a 5.

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 100% and the version parameter's schema text already states 'Defaults to the last saved version' and that a nonexistent version errors, so the description's '(or `version`)' restates rather than extends the schema. With the schema doing the heavy lifting, the baseline of 3 applies; no extra format or semantic detail is contributed.

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?

The description names a specific verb and resource ('List the files microservice.md generates for a service'), enumerates the artifact kinds covered (OpenAPI, AsyncAPI, proto, GraphQL, runbook, ADRs, C4, context pack), and scopes it to a saved version. It also explicitly separates itself from get_service_md, so an agent can distinguish it from siblings without opening any schema.

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?

It gives an explicit downstream routing rule ('Call it to get the paths for get_artifact') and an explicit exclusion with the correct alternative ('For the MICROSERVICE.md itself, use get_service_md'). It also states a conditional follow-up action for hasDraftChanges, which is genuine when-to-use guidance rather than inference.

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