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

Beyond the annotations, the description discloses real side effects: 'Syncs the mirrored calendar event and rebuilds life_state.' It also documents the error condition for unknown or other-user food_id, auth requirements, share-token restriction, and cost. This is valuable behavioral context that annotations do not provide.

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 core mutation and required parameter are front-loaded, followed by the patch list, example, side-effects, auth, and cost in a dense but readable format. There is minor redundancy between 'Requires API key or OAuth' and '($0.10; API key required)', but the length is justified for a 14-parameter mutation tool.

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's complexity, the description covers the required identifier, patch semantics, error behavior, side effects, auth, share-token restriction, and pricing. An output schema exists, so return-value details are not required from the description. An agent has enough information to call update_food correctly and safely.

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 93%, so the schema already documents most parameters. The description adds value by grouping aliases like with / people_names / person_ids and consumed_at / meal_period, and by giving a concrete example of patching only `what` while preserving the rest of the row.

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 'MUTATES one existing Food Diary row the authenticated user owns', giving a specific verb, resource, and ownership constraint. It clearly differentiates from log_food by emphasizing existing rows and explicitly stating that an unknown or other-user food_id 'does not create a row.'

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 establishes food_id as required and frames all other fields as an 'Optional patch', signaling this is the edit tool rather than a creation tool. It references log_food as the field-source sibling and warns that share tokens cannot write, but it does not explicitly say 'use log_food to create a new row.'

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