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

Annotations already declare readOnlyHint=true and idempotentHint=true, but the description adds substantial behavioral context: exact outcome categories, the 5,000-word refusal limit, the meaning of 'normalized' matches, the requirement to check omissions, and version semantics including superseded and update-18-optional states. This goes well beyond the annotations and is highly transparent.

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?

The description is long but every section earns its place: purpose, outcome taxonomy, operational constraints, and version nuances. It is front-loaded with the core purpose. A slight reduction could improve scannability, but the density is justified for a tool with complex result semantics and no output schema.

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?

Given the absence of an output schema and the tool's nuanced outcomes, the description is remarkably complete. It covers exact, normalized, composed, not_found, and not_checked outcomes, explains the omitted-span risk, names the response fields an agent should check, and addresses versioning and update-18 status. An agent has enough context to invoke and interpret the tool correctly.

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 0%, so the description must compensate for the bare parameter definitions. It does clarify that the tool checks a passage of text and that register_id can be passed when known, adding meaning to both parameters. However, it never explicitly names the parameters as 'text' or 'register_id' nor specifies register_id format, leaving some minor ambiguity.

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 opens with a specific verb and resource: 'Check whether a passage of text actually appears in the regulator's source document.' It clearly distinguishes this from sibling tools by emphasizing verification against source documents and even notes it works on text from any source, not just text the server returned.

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 description explicitly says to use this tool to check your own draft answer before presenting it, which is direct usage guidance. It also explains when to pass register_id versus letting up to 3 candidate sources be located by search. It does not explicitly name sibling alternatives or exclusion conditions, so it stops short of a 5.

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