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

Beyond the readOnlyHint annotation, the description discloses critical behavioral traits: hybrid metadata filters, auto-inference with explicit params winning, water-hazard expansion logic, soft filtering for partial data coverage, name_contains exact substring behavior, and specific data-coverage caveats (Tokyo-only toilets, Greater Tokyo ridership). It also explicitly states MLIT hazard categories are relayed 'as-is, NOT a safety judgment.' 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 long but dense and well-structured, front-loaded with the core purpose and then organized by filter behavior, coverage notes, and role split. Every sentence contributes useful information, though a few concepts (soft filters, water-hazard expansion) could be simplified without losing meaning. For a tool with 10 parameters and complex semantics, this length is justified.

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, an output schema exists, and the description still adds necessary context: data coverage limitations, relationship to sibling tools, auto-inference behaviors, and edge cases like name_contains. It doesn't need to explain return values because the output schema covers that. The description leaves no obvious gaps for an agent deciding to use this tool.

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?

Although the schema already documents all 10 parameters (100% schema coverage), the description adds substantial meaning: it explains how auto-inference works, that explicit params override inferred ones, the special limit rule with name_contains, soft_filters for partial coverage parameters, and the semantics of flood_rank_max and accessible_toilet_min. This is far beyond baseline schema descriptions.

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 ('Discover') and resource ('Japanese train stations') and explains the method ('by describing what you want around them'). It also explicitly distinguishes the tool from siblings via the role split: 'station_search finds candidate stations — then get_toilet_by_station / search_ramen / get_station_hazard / get_station_context for detail on one station.'

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 usage guidance and alternatives: it names sibling tools for follow-up detail, explains when to use name_contains ('Use for "stations whose name contains X" requests that semantic search cannot guarantee'), and clarifies what the tool does not do (e.g., taste/quality words not evaluated, coverage limitations). This goes far beyond implied context.

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