List Endpoints

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

Beyond the readOnlyHint annotation, the description discloses meaningful behavioral nuances: setting scope to 'project' changes the return shape and causes specId to be ignored. It also surfaces an operational dependency—"Requires project context (call set_context first)"—which the annotation does not convey. This goes well beyond what readOnlyHint implies and helps an agent anticipate surprising behavior.

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 four sentences with no filler: purpose, version filtering, the project-scope alternative with its behavioral consequence, and the required context. Each sentence introduces a distinct piece of information. Front-loading the main purpose and then layering conditional behavior keeps it both concise and highly informative.

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 tool has two distinct modes and the description fully explains both, including the special collision-grouping output and the ignored specId. It also provides the set_context prerequisite, which is critical for correct invocation. It stops short of describing the default mode's return envelope (e.g., whether it is a bare array or a paginated object), but the presence of skip/take and the explicit contrast with project mode make the behavior sufficiently clear.

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?

Input schema coverage is 100% for all five parameters, so the baseline is 3. The description adds real semantic value on top of the schema by explaining the interplay between scope and specId: in project mode, specId is ignored and the result is not the full list. This clarifies the most complex parameter relationship in the tool, even though skip, take, and versionId remain adequately described by the schema 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 opens with a specific verb and resource: "List all endpoints of an API specification," making the core action unmistakable. It further distinguishes behavior by clarifying the default spec scope versus the project scope, which sets it apart from sibling list operations. Optional version filtering and the special project-mode output are stated clearly, leaving no ambiguity about what the tool does.

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 clear situational guidance: use the default scope for a single spec, or set scope to 'project' to cross specs and detect routing conflicts. It explains the trade-off (grouped collisions plus counts instead of the full list) and notes the prerequisite to call set_context first. However, it does not explicitly compare against sibling tools such as list_linkable_endpoints or get_endpoint, so alternative-tool selection is left to inference.

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