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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety and closed-dataset profile is fully covered without the description. The description does add return-content context (suits, cost level, immigration office) that annotations cannot convey, which is genuinely useful given there is no output schema. It says nothing about result volume, ordering, or pagination, so it adds only moderate value beyond the structured fields.

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 well-formed sentence with the core purpose front-loaded and the useful return-field detail trailing. No filler or restatement of the title. The only weak element is the trailing "or by what the person wants" clause, which is vague and could be dropped or replaced with a reference to the kind parameter.

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?

This is a simple read-only listing tool with two optional parameters and no output schema, so the description's coverage of what is returned and how to filter is close to sufficient. Rich annotations handle the safety and openness questions. The remaining gap is the unattached "what the person wants" filter and the absence of any note on result size or ordering.

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 carry the semantic load for both parameters. It implicitly explains city via "Filter by city" and loosely explains kind via the "neighbourhoods, towns, islands" parenthetical, which matches the enum values. However, it adds no detail on matching behaviour (exact vs partial city names) and introduces an unsupported "what the person wants" filter concept that has no corresponding parameter.

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 ("List Staylong's long-stay places") and immediately scopes what a place is via the parenthetical "neighbourhoods, towns, islands", which maps onto the kind enum. The return content ("who each suits, cost level and immigration office") further pins down the resource. It does not explicitly contrast itself with siblings like check_visa_eligibility or find_immigration_office, though the resource is plainly distinct.

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 guidance is "Filter by city or by what the person wants", which is about filtering rather than when to choose this tool over a sibling. There is no statement of when not to use it, no prerequisites, and no named alternative. Worse, "what the person wants" does not correspond to any parameter in the schema, so an agent trying to follow it has nothing to bind to.

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