location_search

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

Even with readOnly/idempotent/non-destructive annotations, the description discloses material behavior annotations cannot: credit cost (1 per call, +1 for pre-1970), the ambiguous-result contract, conditional return fields (utcOffsetAtDate, provenance fields), and the historical DST caveat ('1987 DST rules differ from today's'). 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?

About 170 words but zero filler — purpose, usage rule, cost, return fields, historical behavior, ambiguity protocol, and param hints each get exactly one sentence, in logical order with the most decision-relevant info front-loaded.

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?

No output schema exists, so the description carries the full burden of return-value disclosure and meets it: return fields, conditional fields, provenance metadata, and the ambiguity outcome are all spelled out. For a 6-param tool with 1 required param and no enums, nothing an agent needs to call it correctly — input, costs, or output — is missing.

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%, so the schema already documents all six parameters and the pre/post-1970 cost split. The description adds value beyond it by explaining that country/region/near act as ranking biases, that a trailing 'City, ST' qualifier in the query is honored, and by reinforcing the date parameter's cost implications. Above the high-coverage baseline because of the extra query-format and ranking semantics.

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 — 'Resolve a place name to coordinates and IANA timezone' — and immediately scopes it against the alternative: 'use this first whenever a user gives a birth city rather than latitude/longitude.' This clearly separates it from sibling tools like timezone_resolve that would operate on already-known coordinates.

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?

States explicitly when to use ('use this first whenever a user gives a birth city'), when not to ('NEVER recall coordinates from memory; always resolve them here'), and how to handle ambiguity ('ASK the user which one they mean rather than assuming the first'). The only unstated alternative is the sibling timezone_resolve, but the 'rather than latitude/longitude' phrasing makes the boundary unambiguous.

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