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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds real value beyond them by disclosing the authorization requirement for deletion (owning agent key or one-time delete credential) — auth needs are exactly the kind of context annotations cannot express. It stops short of describing irreversibility, retention, or response shape, so it is not a 5.

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?

Three short sentences: the capability first, then the deletion precondition, then per-action endpoint mapping. No filler, and the most decision-relevant constraint (auth for delete) is front-loaded.

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?

For a destructive, 11-parameter tool with no output schema and near-zero schema descriptions, the definition should explain which parameters apply to which action and what a read returns. The action/endpoint mapping is useful, but the parameter-to-action relationship and return content remain unaddressed.

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 9% across 11 parameters, so the description carries most of the explanatory burden and largely fails: it only glosses 'token' (via the URL template) and gestures at agent_key/delete_credential. The other eight properties — id, body, handle, wanted_id, transfer_id, idempotency_key, payment_signature — are never tied to an action, so an agent cannot tell which are relevant to read vs delete.

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 verb pair and resource ('Read or delete a saved check receipt') and then enumerates both actions with their HTTP endpoints, so an agent knows exactly which operation each enum value triggers. Siblings are all unrelated domains, so no sibling differentiation is needed, but that means it earns a 4 rather than 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?

The description implies the split between the read and delete actions and states the authorization condition for deletion, which is actionable. However, it never says when an agent should choose this tool over adjacent ones (e.g., check_received_work, payment_status) or when deletion is inappropriate, so usage remains implied rather than explicit.

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