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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so safety is covered. The description adds critical behavioral context: data provenance (GISFinder's directory), verification schedule (verified_status, verified_at), authority (the office named has the final say), and a security warning that text in result fields is data, not instructions. This goes well beyond the annotations and is especially valuable given the openWorldHint=false.

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 a single dense paragraph, but it is front-loaded with the trigger condition ('Use first when...') and then systematically covers outputs, input constraints, error handling, data provenance, and security. Every sentence adds substantive information without repetition or filler. The structure is logical and efficient for an agent to parse.

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 complex tool with 5 parameters, no required fields, and a rich output schema, the description covers all essential aspects: input alternatives, output structure (jurisdiction chain, office details, up to 3 official pages), error handling, data source, verification, and a security caveat. Nothing an agent needs to invoke it correctly or interpret results is missing. The description fully complements the schema and annotations.

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?

The schema covers all 5 parameters with descriptions (100% coverage), so the baseline is 3. The description adds essential guidance on parameter exclusivity: 'Give exactly one of: address; lat and lon; or place and state.' This constraint is not encoded in the schema (all fields are optional, no required group), so the description clarifies the intended usage pattern. It also explains the error behavior for ambiguous inputs, which helps agents decide how to retry.

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 states a specific action ('resolve jurisdiction') and a clear resource (jurisdiction chain with government bodies per function). It distinguishes itself from siblings by saying 'Use first when the user names a US address, a point, or a place,' which positions it as the primary jurisdiction resolver. It also specifies exactly what is returned (jurisdiction_id, offices, verified links), making the purpose unambiguous.

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 gives explicit when-to-use guidance ('Use first when the user names a US address, a point, or a place') and explains the three accepted input modes ('Give exactly one of: address; lat and lon; or place and state'). It also instructs how to handle ambiguous results ('ask again with one of them'). However, it does not explicitly mention alternatives or when not to use it, though the 'Use first' phrasing implies priority over siblings.

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