listCities

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

Annotations already declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint. The description adds critical behavioral details: pagination (cursor-based, limit/page), filter/sort semantics, return format with field descriptions (including the known typo 'locaiton_id'), auth method, rate limiting, error handling pattern, and the empty-result behavior. No contradiction with annotations.

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 comprehensive but somewhat lengthy. It is well-structured with clear sections (use when, pagination, filter/sort, returns, system-critical note, auth/rate limit/errors). Could be slightly more concise, but every section earns its place by providing essential context.

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 complexity (7 parameters, no output schema), the description is remarkably complete. It describes the return format and all fields (including the typo), pagination, filtering, sorting, auth, rate limits, error patterns, and system-critical warnings. It even advises against creating/deleting via API. This fully equips the agent to use 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 coverage is 100% (all 7 parameters documented). The description adds value beyond the schema by explaining how to use filter parameters (property, property_value, property_operator) with examples like 'city_ln', 'city_filename', 'state_sn', 'country_sn', and clarifying the cursor-based pagination parameters. It doesn't cover all possible values but provides useful guidance.

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 clearly states the tool lists cities for location-based search and SEO slug generation. It distinguishes from siblings by emphasizing read-only access and explicitly noting that create/delete are deliberately omitted, referencing updateCity for modifications.

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?

Provides explicit when-to-use scenarios: resolving city name to slug and discovering seeded cities. Also states when not to use: creating or deleting cities, with rationale about slug collisions and member orphan risks, and directs to updateCity for corrections.

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