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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=false and idempotentHint=false. The description adds real context beyond them: the auth material needed (the plan's code and control key), the precondition that the phone session must have been Started, and the fact that the phone user can resume independently. It does not explain the failure surface beyond 'it says so', which keeps it out of the top band.

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 in the first clause, followed by the alternative channel and the precondition, with no filler sentences. The parenthetical aside about resuming on the phone is useful but slightly bulky for the sentence it sits in, so it isn't quite a zero-waste 5.

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?

An output schema exists, so return values need no explanation, and the annotations cover the safety profile. What remains for an agent to call this correctly — the credential requirements, the Start precondition, and the failure behavior before Start — is all stated.

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 description coverage is 100% and both parameters are fully documented in the schema (including the ktpk_ key format and the secret-handling warning), so the schema does the heavy lifting. The description only restates 'Needs the plan's code and control key' without adding syntax or format detail. Baseline 3 is correct.

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?

Specific verb (pause) plus scoped resource (every dish of this plan running on the phone), and it explicitly names the inverse sibling resume_meal so the agent can tell the two apart without opening a schema. The scope qualifier 'that is running on the phone' distinguishes it from meal_status or cancel_meal.

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 a concrete precondition ('Only works after the person has tapped Start on the phone') and points to the alternative path for undoing it ('the cook can resume on the phone or you can call resume_meal'). It doesn't state any case where a different tool should be preferred for the pausing itself, so it stops just short of full when/when-not coverage.

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