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

With no annotations, the description carries the whole burden and does a solid job: it enumerates the four outcome states (pass, fail, not_present, not_checked), explains the special pass_supplied_key state, and discloses the auth requirement ("No API key"). It does not say what a malformed input or a wholly unverifiable record returns, which is the main remaining gap.

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?

Dense but front-loaded: the purpose lands in the first clause, then output semantics follow in short declarative sentences. Each sentence contributes information; nothing is padding. Slightly list-like, but appropriate for a multi-mode verifier.

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 a nested, untyped `record` object, zero schema descriptions, no annotations, and no output schema, the description does well on return vocabulary but leaves the caller guessing what to put in `record` and whether the three parameters are alternatives or combinable. For a tool this open-ended, that is a meaningful gap.

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% across three undocumented parameters, so the description must compensate. It partly does: `public_key_pem` is explained via the caller-supplied-key / pass_supplied_key semantics, and `record` vs `bundle_base64` map to the two verification modes. But the shape of the nested `record` object and base64 encoding of the bundle are never described.

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+resource ("Check a record or export bundle") and immediately enumerates what the check reports (signature, public timestamp, RFC 3161 timestamp, hash chain, file_hashes vs manifest). This is far more than a restatement of the name. It does not, however, differentiate itself from nearby siblings like verify_agent or check_action.

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?

No when-to-use or when-not-to-use statement, and no mention of the sibling tools an agent might confuse this with (verify_agent, check_action, scan_mcp_tool_result). The agent must infer from the input types that a `record` goes with record verification and `bundle_base64` with bundle verification, but mutual exclusivity is never stated.

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