get-pce-capacity

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

With no annotations, the description carries the full burden and does so well: it names the undocumented root-level endpoints probed, maps 403 to 'exists but this key is not allowed' (and discloses the authorization_failed audit event), maps 404 to 'not on this PCE version', and explains the 200 pass-through. It also warns that probing without permission writes an audit event and defines the `warnings` threshold (>=80% of a limit or above a soft limit).

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?

Front-loaded with the core question, then ordered by data source, error semantics, and the warnings field. It is dense and somewhat run-on in the middle clause, but essentially every sentence earns its place by adding behavioral or return-value information.

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?

No output schema exists, so the description must cover returns; it defines `warnings` and the three probe outcomes (403/404/200), which is substantial. It stops short of describing the shape of the metrics payload itself, but for a 2-param diagnostic tool the coverage is nearly complete.

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%, so both parameters are already documented, establishing the baseline of 3. The description reinforces the object-limit probing behavior and audit-event side effect but adds no syntax, format, or default detail beyond what the schema already states.

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?

Opens with a specific, memorable framing: 'How full is this PCE, against its limits.' The verb+resource (capacity/limit assessment of a PCE) is unambiguous and clearly distinct from every sibling, none of which report capacity. An agent can select it without opening the 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?

The purpose strongly implies a diagnostic/health-check use case, but there is no explicit when-to-use or when-not-to-use wording, and no named alternative (e.g., check-pce-connection or enforcement-readiness) is contrasted. Usage is inferable but not stated.

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