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

With readOnlyHint=false, the description usefully adds that the call is not safe to repeat blindly, uses the Worker's private key, and grants no permissions. But it also creates confusion by saying 'even though no database row changes' while later stating 'WRITES: this call changes stored state,' without reconciling what state actually changes.

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 front-loaded with the core action and is reasonably compact for a security-sensitive tool. Some phrasing, especially the 'no database row changes' versus 'WRITES' contrast, could be tightened to avoid ambiguity.

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 tool with no output schema and fully documented input schema, it covers key invocation context: endpoint availability, private-key use, identity-only scope, and non-idempotence. It stops short of describing the returned credential format and leaves the state-change wording ambiguous.

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 the schema already explains the audience, nonce, and secret parameters. The description reinforces 'exact HTTPS audience' and 'one-use nonce' but does not add material syntax or semantics beyond what the schema provides.

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 gives a specific verb and resource: 'Mint a five-minute Square-signed EdDSA identity credential' for an external project's exact HTTPS audience and one-use nonce. It also scopes the tool as identity-only and explicitly says the assertion grants no permissions, which distinguishes it from permission-granting or state-changing siblings.

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?

It indicates the tool is for an external project that needs an identity assertion and notes the 'Full /mcp endpoint only' constraint. However, it does not name alternatives such as issue_attestation or explain when not to use this tool versus those sibling tools.

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