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

The description adds real behavioral context beyond the annotations: it discloses that output includes evidence quotes and explicit coverage, and that canon is never modified. However, the annotations declare readOnlyHint=false and destructiveHint=true, and the description never explains what side effect actually occurs (work-run creation, model consumption, stored review artifact), leaving the agent with an unresolved tension between 'never changes canon' and a destructive hint.

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?

Three dense sentences, front-loaded with purpose, then output contract, then the long-document procedure. No filler or repetition; the only mild cost is that the long-document sentence sits in the description rather than being tied to the passages parameter it governs.

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 need not be spelled out, and the description still characterizes them. But for a six-parameter, nested-object, model-backed tool with destructive annotation coverage, the definition leaves the side-effect profile and the relationship to the sibling continuity checker unaddressed.

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?

With 50% schema description coverage, the schema already documents resource_id, expected_revision, read_skills and expected_catalog_version in detail, while 'question' has an empty description. The phrase 'exact current passages' reinforces that revisions must be current, but the description does not explain the question field, request_key, or work_id, so it only partially compensates for the 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 and target: review semantic contradictions and missing facts across exact current passages using the selected model, and it names the deliverable (evidence quotes, revisions, explicit coverage). An agent knows exactly what the call produces. It stops short of differentiating itself from the sibling native.check_continuity, which sounds like the nearest alternative.

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 only procedural guidance is for long documents: 'repeat bounded sections and finish with a global comparison', which tells the agent how to sequence calls but not when to choose this tool over check_continuity or a plain read. There are no explicit exclusions, prerequisites (e.g. the read_skills proof requirement), or cost/scope caveats.

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