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

Goes beyond the annotations by disclosing the key behavioral guarantee: the embedded hash is never trusted and the digest is recomputed, and the result is scoped to jobs this hive ran. Annotations already cover read-only, idempotent, non-destructive and closed-world, so this adds genuine security-relevant context rather than repeating it.

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 dense clauses with zero filler; the recompute-and-compare behavior is front-loaded and the parenthetical caveat earns its place by flagging the trust model.

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?

An output schema exists, so return-value explanation is unnecessary, and annotations plus the trust-model sentence make the behavior clear for a one-parameter tool. The only shortfall is that the accepted format of audit_json is not described anywhere.

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 0%, so the single audit_json parameter is undocumented in structured form; the description only hints that it carries a 'presented lineage' with an embedded hash. It adds partial meaning but does not state the expected JSON shape or required fields, leaving a real 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?

States a specific verb+resource pair: 'Recompute the audit digest' and 'report whether it matches a job this hive ran'. An agent can tell this is the verification counterpart to audit_job without opening a schema, though the sibling is never named explicitly.

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 by the phrase 'from a presented lineage' and 'whether it matches a job this hive ran', which suggests the check-audit scenario. There is no explicit when-to-use/when-not-to-use guidance and no direct comparison against audit_job or job_status.

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