Review queue

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

Annotations already cover read-only, idempotent, non-destructive and closed-world, so the bar is low; the description adds real semantic context by defining what is queued and by warning that confidence_v2 is a review-priority signal, not a probability — a genuine misreading risk it pre-empts. It does not discuss volume, truncation, or empty-queue behavior.

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?

A single dense sentence with the headline concept front-loaded, then item classes, then output fields, then the confidence_v2 caveat. The parenthetical list is long but every element carries information, and nothing is redundant.

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?

For a zero-required-param read-only list tool with full annotations and no output schema, the description conveys both what is returned and the key interpretation caveat. The remaining gaps — result shape, ordering guarantee, limit ceiling semantics — are minor and partly covered by the schema.

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 67% and the two documented params (sort, include_samples) already carry descriptions, so the schema does most of the work. The description's confidence_v2 gloss does clarify what sort='confidence_v2' means, but it says nothing about limit or how samples affect results — a baseline 3.

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 names a concrete artifact — a prioritised human review queue — and enumerates the item classes it contains (withheld/ambiguous links, inferred states, false COMPLETE with active risk) plus the payload fields (reasons, score, confidence_v2). An agent can distinguish it from ghost_summary or ghost_list_cases on content, though no sibling is 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?

The word 'human review' implies a triage/audit use case, but there is no explicit statement of when to prefer this over ghost_list_cases or ghost_summary, and no exclusions or prerequisites. Usage is inferable rather than stated.

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