garmin_raw

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context beyond annotations: it is 'compacted and hard-capped,' 'bounded,' and tied to a single named source. This gives the agent a clear expectation of constrained, raw output, though it does not detail response formatting or edge cases.

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 two sentences with no filler. It front-loads the core concept ('Bounded escape hatch'), immediately adds usage restrictions, and ends with a clear prohibition. Every phrase earns its place, making it highly concise and well-structured.

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 that an output schema exists and annotations cover safety, the description does not need to explain return values or destructive behavior. It provides essential context about boundedness, raw values, and usage policy. It does not enumerate all source-specific dependencies, but the schema covers those details, so the description is reasonably complete for a deliberately constrained escape-hatch 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 description coverage is only 40%, so the description should compensate. It only implicitly references 'source' via 'one named Garmin source' and 'hard-capped' via max_points, but provides no guidance on date, series, or activity_id dependencies. The schema itself documents activity_id as required for activity_* sources and weather, but the description adds minimal parameter-level value.

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 conveys that this is a bounded way to access raw values from a single named Garmin source, and explicitly contrasts it with synthesis tools by saying 'Use ONLY when a synthesis tool cannot answer and the user explicitly asks for raw values.' However, it relies on the metaphor 'escape hatch' instead of a direct verb like 'retrieve' or 'fetch,' so it is clear but not maximally explicit.

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 when-to-use guidance: only when a synthesis tool cannot answer and the user explicitly requests raw values. It also states a firm exclusion: 'Never a starting point.' This clearly distinguishes it from sibling synthesis tools and prevents inappropriate first-use.

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