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

With no annotations provided, the description carries the full burden of disclosure and does so excellently. It reveals JWS signing, operator-gated access via admin_token checked against REVETTR_ADMIN_TOKEN, disabled behavior when env var is unset, sensitivity of admin_token in MCP transcripts, and verification steps against JWKS. These are substantive behavioral traits beyond basic action.

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 four sentences, each adding essential information: purpose, compliance context, authentication, and verification. It is somewhat lengthy but not verbose; every sentence contributes to operational understanding. No wasted words.

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?

Given the tool's complexity (auth, signing, compliance) and presence of an output schema, the description covers key operational aspects: JWS signing, verification procedure, disabled state, and sensitivity of logs. It doesn't detail error conditions, but the output schema likely handles return format. The reference to docs/audit-trail-export.md adds completeness.

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 0%, so the description must compensate. It explains wallet_address and admin_token but entirely omits start and end parameters, leaving their purpose ambiguous. For a tool with four params, this is a significant gap.

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 clearly states the tool's function: 'Export a JWS-signed audit-trail bundle of scoring decisions for a wallet.' This is a specific verb+resource combination that distinguishes it from sibling tools like score_counterparty (scoring) and verify_issuer (verification). The mention of the MCP equivalent of GET /v1/audit/export further clarifies its role.

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 provides clear usage context by labeling it as a 'Compliance artifact for EU AI Act Article 12 logging / NYDFS certification / debanking-defense.' It also notes operator-gating and prerequisites (admin_token, env var). However, it does not explicitly mention alternatives or when not to use this tool, so it falls short of a 5.

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