list_capabilities

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the description doesn't need to repeat those. It adds value by specifying the return fields (capability_id, kind, provider_id, binding_id, execution_owner, tags) and explicitly notes 'Read-only.' There is no contradiction with annotations. The description provides additional context about what the caller receives beyond the annotation's safety profile.

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 concise and well-structured. It front-loads the purpose, then explains filtering, then points to alternatives, and ends with the return fields. Every sentence earns its place, and there is no fluff. It is appropriately sized for the tool's complexity.

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 is fairly complete for a listing tool. It covers the purpose, filtering options, alternatives, and return fields. There is no output schema, so the description compensates by listing expected fields. It does not mention pagination or result limits, but for a capability catalog this may not be critical. The mention of relevant siblings covers routing. Overall, it provides enough for an agent to call 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%, so each parameter is already documented (e.g., 'Keep only these capability kinds.'). The description mentions filtering by kinds, provider_ids, or binding_ids, but this merely restates the schema's meaning without adding new semantics. It does not clarify value formats, relationships, or any nuances not already in the schema. Thus the baseline of 3 applies.

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 clearly states the tool lists the unified capability catalog, enumerates the kinds of entries (datasets, MCP tools, resources, prompts, skills, native tools, runtime libraries), and mentions filtering. It explicitly differentiates from siblings by naming get_capability, route_capabilities, and list_skills for specific use cases. The verb 'list' and resource are specific.

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?

Provides explicit guidance on when to use this tool versus alternatives: 'Use get_capability for one entry's detail, route_capabilities to pick the best entry for an objective, and list_skills for the skill subset.' Also states it is read-only, which signals safe invocation. The conditions for filtering are clear.

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