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

Annotations already declare readOnly, idempotent, and non-destructive behavior, so the description's burden is reduced. It adds useful context by specifying exactly what the returned contract contains: typed request, response, metering, and readiness. This goes beyond the bare schema and helps set expectations about the data's composition.

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?

A single, tightly constructed sentence with no filler. Key information (verb, resource, scope) is front-loaded, and every word contributes to understanding the tool's contract retrieval purpose. It is modeless and to the point.

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?

With a hidden output schema, a fully documented parameter, and safety annotations, the description is sufficient for an agent to select and invoke the tool correctly. The only minor gap is a lack of explicit 'when not to use,' but the 'one exact capability id' phrasing makes the intended scope obvious. Nothing essential for correct invocation is missing.

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%, yet the description adds meaning by specifying the capability_id as an 'Exact capability id returned by pubfi.capabilities.list.' This provenance information is not present in the schema itself and gives the agent a clear way to obtain a valid parameter value. The over-arching description also reinforces the single-id semantics.

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 uses a specific verb, 'Return', and identifies a precise resource: the full typed contract for one exact capability id. It clearly distinguishes this from pubfi.capabilities.list by emphasizing 'one exact capability id' versus a list operation. An agent can unambiguously understand the tool's function.

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 makes clear that this tool targets a single exact capability id, implying the id comes from a prior listing operation. It provides context for when to use it, though it does not explicitly name alternatives or state exclusions. The sibling tool list reinforces the intended workflow without needing explicit guidance.

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