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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real behavioral value beyond that: the five gate families it applies, the three possible verdicts (publish, caution, claim-level abstain), and the policy that sensitive topics stay answerable with bounded reflections. That is meaningful disclosure for a decision tool.

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 tight sentences, front-loaded with the action and verdict set, then the sensitive-topic policy. No filler, though the dense gate jargon goes unexplained, which slightly undercuts readability.

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 values needn't be spelled out. But for a 10-parameter audit tool the description leaves the entire input contract — especially harmClass and the evidence arrays — to an undocumented schema, and gives no routing guidance among the several sibling audit tools.

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?

Ten parameters with 0% schema description coverage, so the description carries the full explanatory burden — yet it documents none of them. The gate names ('calculation', 'approved-rule', 'opposition', 'calibration', 'harm') loosely hint at calculationCertified, approvedRules, opposingEvidence, empiricallyCalibrated and harmClass, but nothing is explicit, and the enum for harmClass is never explained.

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 and resource (audit one prediction claim) and adds a sequencing cue (before narration) that separates it from generic audit siblings. It does not, however, name or differentiate itself from the closely related assess_prediction_readiness or audit_reading_evidence tools.

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?

'Before narration' implies the point in the workflow at which to call it, but there is no explicit when-to-use versus assess_prediction_readiness / audit_reading_evidence / audit_chart_calculation, and no stated prerequisites or exclusions. Usage must be inferred.

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