Directions

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

The annotations already declare readOnlyHint and openWorldHint, and the description adds meaningful behavioral context by disclosing that it uses Google if a key is available, otherwise falls back to straight-line km. This conditional behavior is valuable and goes beyond the structured annotations. However, it does not elaborate on network dependency or response variability.

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 extremely short and front-loaded, with no unnecessary words. The key behavioral distinction is packed into the parenthetical. While it reads more like a fragment than a complete sentence, it is concise and efficient for the information it conveys.

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 has three parameters with zero schema descriptions and no parameter documentation in the description, an agent would likely struggle to invoke it correctly. The description does not explain origin/destination formats, allowed mode values, or when the Google path is used versus the straight-line fallback in practical terms. Output schema exists, so return value structure is less critical, but the missing parameter semantics and usage guidance leave noticeable gaps.

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 0%, so the description carries the burden for parameter meaning. Origin and destination are self-explanatory by name, but 'mode' is not described at all beyond its default value, and the description does not clarify accepted formats (e.g., addresses vs coordinates) or how mode affects the outcome. The mention of 'straight-line km' hints at output units but not parameter 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 title 'Directions' plus the description 'Directions (google with key, else straight-line km)' clearly identifies the tool as computing directions between an origin and destination. The parenthetical also distinguishes it from geocoding by mentioning straight-line km and Google. However, it lacks an explicit verb like 'calculates' or 'returns', which would make the purpose fully 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 gives no guidance on when to use this tool versus alternatives such as maps_geocode or other mapping-related tools. There are no explicit use cases, prerequisites, or conditions that would help an agent decide between this and a sibling tool. The only contextual hint is the fallback behavior, which is about execution, not selection.

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