fitbit_get_food_log

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

With no annotations, the description discloses valuable behavior: caching with auto-sync, 'live' mode using one API call per day, and the omission of days with no logging. These details go beyond a basic read operation, but still missing auth requirements or error handling.

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 broken into clear sections: purpose, return summary, behavioral notes, and parameter explanations. Every sentence contributes value, with no redundancy or filling space.

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?

The tool has only 3 simple parameters and an existing output schema, yet the description still covers return shape, cache behavior, live mode, and data availability rules. This is more than sufficient for an agent to select and invoke it correctly.

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 0%, but the description fully explains all three parameters: date formats for start_date, defaults for end_date, and the semantic and cost implication of live. This precisely compensates for the schema's lack of parameter 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 'Get daily food and water log summary' – a specific verb, resource, and scope. It clearly differentiates from sibling tools like fitbit_get_activity or fitbit_get_sleep by naming the exact data domain (food/water).

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 implies when to use the tool (for food/water data) and gives important context about data being only present if the user logs in the Fitbit app. However, it does not explicitly name alternatives or exclusion conditions, so it stops short of full 'when not to use' guidance.

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