log_meal

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

The annotations already declare idempotentHint=true and readOnlyHint=false, which signals a safe-to-retry write operation. The description adds the note that estimates are 'caller-supplied' and that an idempotency key is used, which is useful behavioral context about retry semantics. However, it doesn't disclose what the response contains or whether items can be optional (the schema shows a default of []). With annotations present, this is adequate but not rich.

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 a single sentence with zero waste. It's concise and front-loaded. However, it's arguably too thin given the 16-parameter schema, but for what it states, it's efficient.

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?

Despite having an output schema (which shifts some burden), this is a complex 16-parameter tool with 0% schema description coverage. The description does not explain the relationship between estimated_total_* and items, whether items are optional alternatives to totals, or how idempotency_key should be generated. For a write operation with this many interdependent parameters and no parameter-level documentation, the description is substantially under-specified.

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?

With 0% schema description coverage and 16 parameters (6 required), the description must compensate, but it only names two parameters (estimates and idempotency_key) without explaining their semantics. It doesn't clarify the relationship between estimated_total_* fields and the items array (are items derived from totals, or separate?). The schema provides names but no guidance on how items and totals interact, which is the crux of this API.

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 'Log a meal using caller-supplied estimates and an idempotency key,' which clearly identifies the verb (log) and resource (meal) and distinguishes it from sibling tools like get_meal, update_meal, and delete_meal which are read/modify/delete operations. It doesn't differentiate from update_meal, but the 'Log' verb combined with readOnlyHint=false and idempotentHint=true clearly signals a creation action.

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. It doesn't mention that this is for creating new meals (vs update_meal), doesn't explain the idempotency key's role in preventing duplicates, and doesn't note any prerequisites like authentication. A caller must infer usage from the name and schema alone.

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