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

Annotations are absent, so the description bears full responsibility for disclosing the tool's behavior. 'Find latitude and longitude' accurately conveys a read-only geocoding lookup. However, important behavioral traits go undisclosed: the tool can return multiple matches (implied by the count parameter), there's no mention of no-match behavior, and the coordinate format isn't specified. The description is accurate but shallow—it could easily have added a caveat about ambiguous place names or rate limiting without much effort.

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?

Two sentences, no filler. The first sentence is the core purpose, the second adds workflow value by connecting the output to sibling tools. Every word earns its place, and the structure is maximally front-loaded—an agent scanning the first sentence knows exactly what this tool does.

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 low-complexity tool (2 flat params, no nested objects, no enums), the description is nearly complete. The 'use the coordinates with the other tools' line provides crucial integration context, and the description's mention of 'latitude and longitude' gives a hint about the return shape even without an output schema. The main gap is the lack of explicit discussion of multi-match (returned array of candidates) behavior, which the count parameter implies—but this is a minor omission for an otherwise simple lookup 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?

Schema coverage is 100% with both parameters well-documented ('name' includes 'Place name, e.g. 'Bergen' or 'Oslo, Norway'' and 'count' includes 'Maximum number of matches to return' with min/max constraints). Per the rubric, high coverage gives a baseline of 3, and the description doesn't need to add parameter detail. The description's phrasing 'for a place name' echoes the name parameter without restating the schema. The schema carries the weight here, exactly as intended.

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 states a clear verb+resource: 'Find latitude and longitude for a place name.' The name 'geocode_location' and the description's mention of coordinates make the operation unambiguous. The sibling tools are all weather/forecast endpoints, so this tool naturally stands apart as the geocoding prerequisite, and the description makes that distinct role clear. It could be more explicit about disambiguating the output to a single canonical place, but the core purpose is unambiguous.

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's second sentence, 'Use the coordinates with the other tools,' provides valuable workflow context: this tool is a prerequisite step that feeds the forecast/station siblings. This implicitly tells the agent when to reach for this tool (when it has only a place name and needs coordinates for get_forecast, etc.). It doesn't name specific alternatives or when-not-to-use conditions, but given the siblings are all weather consumers of this tool's output, the context is clear.

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