subway_nearby

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

No annotations are provided, so the description carries the full burden. It discloses that results are sorted nearest-first, that the response includes live open/closed status and feature flags, and that store_id is shared with the menu endpoint. It also clarifies the exact-one-search-mode constraint across query/latitude-longitude/store_id. It doesn't mention pagination behavior beyond the offset parameter, but the schema already documents offset as an opaque cursor, so the description adds meaningful behavioral context without contradicting anything.

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 dense but well-organized: it front-loads the core purpose and return fields, then the sitemap contrast, then the store_id relationship. Every sentence earns its place. It is slightly long, but the length is justified by the need to disambiguate from subway_sitemap and subway_menu. A small deduction for the somewhat run-on final sentence.

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 7-parameter tool with no output schema and no annotations, the description covers the key decision points: what the tool returns, how it differs from the sitemap, how store_id links to the menu endpoint, and the mutually exclusive search modes. It doesn't describe the exact response shape, but with no output schema that would be useful; however, the description's mention of distance, live status, payment methods, catering link, and feature flags gives the agent a solid mental model. The main gap is not stating what happens when no stores are found or how errors surface.

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 100%, so the baseline is 3. The description adds value by explaining the relationship between the three search modes (query, latitude/longitude, store_id) and stating 'exactly one search mode', which is not fully explicit in the individual parameter descriptions. It also clarifies that store_id can come from a prior nearby result or from GET /subway/store. This goes beyond the schema's per-parameter text.

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: 'Search Subway stores near a coordinate or address.' It then enumerates the return fields (distance, live open/closed status, payment methods, catering link, feature flags) and explicitly contrasts itself with the sibling subway_sitemap, which is the bulk-scraping endpoint. This makes the tool's purpose unmistakable and distinguishes it from nearby siblings like subway_store and subway_menu.

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 states when to use this tool versus the sitemap: 'This is the proximity search GET /subway/sitemap cannot do directly -- the sitemap enumerates the whole world for bulk scraping, this answers "what is near this point"'. It also explains the relationship to subway_menu via store_id, telling the agent that store_id can be passed back to re-read one store's live attributes. This is explicit when/when-not guidance with named alternatives.

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