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

Annotations already declare non-read-only, idempotent, non-destructive behavior, so the bar is lower, but the description goes further: it discloses what is persisted (consent version, time, connected app, user's words) and the side effect of logging a pending meal. It could say more about failure handling if the version mismatches, but the added context is substantial.

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?

Three dense sentences that are front-loaded with the purpose and the consent-validity constraint, followed by storage side effects and the withdrawal path. Every sentence carries information, though the prose is a little packed.

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 consent-recording mutation with full annotation coverage and an output schema, the description covers the authorization requirement, the stored fields, the meal-logging side effect, and how consent is withdrawn. Nothing needed to invoke it correctly is missing.

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 genuine semantics: user_statement must be the user's own words and version corresponds to the consent text shown. This clarifies intent beyond the enum and maxLength in the schema.

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 names a specific verb and resource ('Records the user's consent to Forkmate storing and processing their health-related data') and adds the downstream effect ('logs any meal that was waiting for consent'). This is clearly distinguishable from siblings like log_meal or update_preferences.

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 states the triggering context (a refused log reply shows the consent text), an explicit exclusion ('an assistant agreeing on the user's behalf is not consent'), and where withdrawal happens (Forkmate Settings). When-to-use and when-not-to-use are both covered.

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