service_requests_near

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

With no annotations, the description carries the full disclosure burden. It effectively discloses the lack of an open/closed status field, the internal field observation proxy, the 'most recent first' ordering, and the point+radius query mechanism. It does not cover edge cases like the precedence if both address and lat/lon are provided, and there is no mention of permissions or rate limits, but for a read-only query tool the disclosed behaviors are significant.

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 concise yet complete, leading with a one-sentence summary of the tool's purpose, then clearly separating Args and Returns. Every sentence adds value: the note about the missing status field, the parameter explanations, and the output structure are all essential. No filler or repetition.

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 tool's complexity (6 optional parameters with conditional requirements), no annotations, and no schema-level descriptions, the description provides a thorough overview. It explains the input alternatives, the return payload fields, and the subtle field semantics. The presence of an output schema reduces the need to dive deeper into exact return types, but the description still covers the key behavioral context. The description is complete enough for an agent to select and use this 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?

The schema provides almost no descriptions (0% coverage), so the description must fully compensate. It does: 'address' is explained as a free-form string with an example, 'lat'/'lon' are described as a pair used when address is not given, 'radius_m' has a default and meaning, 'days' is explained, and 'limit' is explained. This goes far beyond the schema's raw types and defaults.

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 '311 service requests near a point, from the point-level ServiceRequests311 layer,' which clearly states a specific verb, resource, and scope. It distinguishes itself from sibling 'near' tools by clearly targeting 311 service requests and noting the spatial query type.

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 clear context on how to invoke the tool: the address vs lat/lon alternatives, the radius, days filter, and limit. It also notes the absence of a status field, which guides result interpretation. However, it does not explicitly name alternative tools or state when not to use this tool, so it misses the full 'explicit exclusions/alternatives' bar.

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