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

Annotations declare this is a non-read-only, non-destructive write; the description adds substantive context beyond that: the consent model (draft puts a one-tap card in the Stream, send does it now, off refuses) and the hard rule that a household with someone under 18 is always a draft. These behavioral constraints are exactly the kind of context annotations cannot carry.

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?

Purpose is front-loaded and every clause carries non-redundant information (choose semantics, prerequisite, consent modes). It is dense and reads as a run-on with multiple semicolon-joined clauses, which costs a little readability, but nothing is filler.

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?

With an output schema present and annotations carrying the safety profile, the description still supplies everything an agent needs: prerequisite (read_dinners), permission constraints, and the consent/under-18 behavior. Nothing material to correct invocation 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; the description marginally exceeds it by qualifying the choose parameter's real-world constraint (only where the person picks dinners and only when asked), which the schema's own description only hints at. Other parameters (date, title, household, ingredients) are fully handled by 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?

States a specific verb (suggest a dinner) and resource scope (for a day in the household), and clarifies the escalation to actually choosing that day's dinner via choose: true. An agent can distinguish this from read_dinners and other household tools without opening any schema.

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?

Gives explicit conditions: choose only works where the person picks dinners (e.g. parents in a family) and only when they asked for it, and directs the agent to check read_dinners' allergies/preferences first. It also spells out the consent flow selecting between draft/send/off, which is clear when-to-use guidance.

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