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

Beyond the readOnly/idempotent annotations, it discloses an access-control rule that materially changes the answer: the supplier's key sees state, check and dispute but not the result. It also explains conditional visibility – pay_link while held, what_happened on failure, full result once paid – which is exactly the behavioral context an agent needs.

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 front-loaded sentence that leads with the verb and resource, then packs the returned-field inventory into one clause without redundant restatement of the title. Dense but every clause carries 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?

With no output schema, the description effectively serves as the return contract, listing conditional fields per state and per key. Terms like 'check' and 'the sample' are left unexplained, a minor gap for an otherwise self-contained read tool.

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 0%, so the description must carry the parameters, and it does explain the agent_key/api_key precedence rule and that call_id identifies one part call. It does not say where those keys or the call_id come from, leaving a small gap for a mutation-free read tool.

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?

Specific verb and resource: 'Read one part call by call_id with the key that made it', and it enumerates the returned facets (state, check, sample, result, dispute). It is distinguishable from capability_call (which creates a call) by implication rather than by naming the sibling, so it falls just short of a 5.

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?

Usage is implied – read a call you already made – and the key-selection rule (agent_key vs api_key, the caller's key wins) sets context for retrieval. There is no explicit when-to-use/when-not guidance or pointer to related tools such as capability_call_unlock or capability_call_dispute, which the unlock/dispute fields clearly imply.

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