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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuine context the annotations cannot: that the result reveals what it counts on audit.capture, that Merkle root and signing key appear only 'once sealed', and that evidence is never returned inline. This state-dependent disclosure is real added value.

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?

Two sentences, front-loaded with the resource ('One audit: ...'), no filler. It is dense with domain jargon, but each clause carries distinct information about the returned fields.

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?

There is no output schema, so the description carries the full burden of describing the return shape, and it does so comprehensively for a getter. Minor gaps remain (behavior on a missing or unsealed audit, error semantics), but the essential return contract is covered.

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% for the single audit_id parameter, which documents its source (audit.audit.list or audit.audit.create). The description adds no parameter-level detail, so the baseline 3 is correct.

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 enumerates exactly what a single audit record contains (state, page counts, compliance result, capture counts, and sealed Merkle root/signing key), which clearly separates it from audit.audit.list (many) and audit.audit.create (write). It lacks an explicit retrieval verb, but the required audit_id in the schema and the 'One audit' framing make the getter purpose unambiguous.

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 rather than stated: the reader infers you call this to inspect a single audit, likely after create/list. The note that 'The evidence bundle is a resource, never inline' gives a routing hint away from this tool, but there is no explicit when-to-use or when-to-choose-a-sibling guidance.

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