Prepare: Log Food Entry (FatSecret)

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

Annotations declare readOnlyHint=false, but the description clarifies that this is a dry-run and 'Nothing is written until commit confirms' – adding crucial behavioral nuance beyond the annotation flags.

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 short sentences, front-loaded with the key 'Dry-run' label, with no redundant content.

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 description covers the prepare/commit workflow and non-writing behavior, but with no output schema and minimal parameter guidance, the agent may struggle to correctly fill all required fields. It does not explain what the prepared operation should return for commit.

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% for 7 parameters, and the description only elaborates on servingId ('use fatsecret_pick_serving first to get servingId'). Other parameters like foodEntryName, numberOfUnits, meal, and reason rely solely on schema types/names, which is insufficient.

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 'Dry-run: prepare logging a food into your diary', which clearly states the verb+resource. It distinguishes from edit/delete siblings by explicitly targeting creation and referencing the prerequisite pick_serving step.

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?

It instructs the agent to use fatsecret_pick_serving first to obtain servingId, and states that nothing is written until fatsecret_commit_prepared_operation confirms. This provides clear workflow context, though it does not explicitly exclude edit/delete scenarios.

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