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

Annotations only declare non-read-only, idempotent, non-destructive; the description adds the substantive behavior the agent could not otherwise infer: it persists consent version, timestamp, connected app and the user's words, and then logs any meal that was waiting on consent. It also flags the authority constraint (assistant consent invalid) and where withdrawal lives, which matters for a health-data write.

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 opening clause front-loads the core action and the constraints follow in priority order with no filler. The phrase 'as summarised in the consent text that a refused log reply shows' is slightly convoluted, but no sentence is extraneous.

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?

For a two-parameter mutation with a rich annotation profile and an output schema, the description covers purpose, authority constraint, side effects (storing fields then logging a pending meal), and off-ramp (Settings withdrawal). Nothing an agent needs to invoke it correctly is left implicit.

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 100%, so the baseline is 3, but the description adds real semantics: user_statement must be the user's verbatim words rather than a paraphrase, and version corresponds to the consent text shown in the refused reply. That constrains how the agent fills the enum and the free-text field beyond the schema's own wording.

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?

States a specific verb and resource: recording the user's consent to Forkmate storing/processing health-related data. It also anchors the action in a concrete trigger (the consent text shown by a refused log reply), so the agent knows exactly which resource this mutates and how it differs from every sibling (log_meal, get_preferences, etc.).

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 gives a clear admissibility condition — only the user's own explicit agreement in this conversation counts, and an assistant agreeing on their behalf is not consent — plus a redirect for the opposite operation (withdrawal happens in Forkmate Settings). That covers when to use and when not to, though it doesn't name a sibling tool for the non-consent paths.

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