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

Annotations already provide readOnlyHint, so the bar is lower. The description discloses non-obvious behavior not captured by annotations: when scope='project', it returns groups of endpoints colliding on method and path plus counts, not the full list, and ignores specId. It also mentions the set_context prerequisite, which an agent needs to know.

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 description is three sentences, each carrying unique information: listing behavior, the project-scope alternative, and guidance versus get_endpoint. It is dense but not verbose; the only slight complexity is the project-scope explanation, which condenses multiple details about conflicts, counts, and specId being ignored.

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?

The description covers purpose, parameter interplay, prerequisites, and distinguishes the tool from get_endpoint. It does not specify output format, but there is no output schema and pagination defaults are in the schema. Overall, it gives enough context for an agent to use the tool correctly without requiring additional lookup.

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% with descriptions for all five parameters, so the baseline is 3. The description adds crucial interaction semantics: specId is ignored when scope='project', versionId filters by a specific version, and skip/take control pagination—clarifications not inferable from the individual parameter descriptions alone.

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 states 'List all endpoints of an API specification' with a specific verb and resource, and clarifies the project-scope behavior that returns routing-conflict groups. It explicitly contrasts with get_endpoint ('for one endpoint in full use get_endpoint'), making the tool's purpose distinct among siblings.

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?

The description gives direct when-to-use guidance: 'Use this to browse endpoints or find an endpoint id; for one endpoint in full use get_endpoint.' It also explains the alternative 'scope' mode and notes the prerequisite 'Requires project context (call set_context first),' leaving no ambiguity about when to call this vs. other tools.

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