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

With no annotations, the description carries the full burden and does so well: it discloses execution location ('runs on the agent's Mac'), queueing when busy, and a non-obvious side effect ('a done task opens again'). It also states the rate limit ('up to 30 messages and OKs an hour'). It stops short of saying what happens when the limit is exceeded or what errors look like, keeping it below a 5.

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?

Front-loaded with the purpose and audience before the behavioral detail, and every clause carries information. The heavy parenthetical nesting ('shown as sent via this client, and runs on the agent's Mac (queued if it's busy; a done task opens again)') makes it denser than it needs to be, but nothing is redundant.

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?

No output schema exists, and the description largely compensates by explaining the wait_seconds reply behavior, queueing, and the reopen-a-done-task side effect. The remaining gap is that it never says what is returned when wait_seconds is omitted or zero, leaving the agent unsure whether it gets a confirmation, an ID, or nothing.

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 0%, so the description must define all four parameters, but only wait_seconds gets real treatment ('up to 50', waits for its reply). For 'agent' and 'task' it never says whether they are IDs, names, or handles, which is the key ambiguity for locating the target. 'message' is clarified conceptually but not in format.

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 action on a specific resource: 'say something in an agent's existing task, with all of its context'. It also scopes the audience ('for clients outside Caddie acting for the user') and explicitly names the sibling it is not ('To OK a draft or a proposal, use task_approve'), so an agent can separate it from task_approve and task_stop 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 an explicit routing rule to an alternative (task_approve for drafts/proposals) and demonstrates the intended content with examples ('an answer to its question, the next step'). It also names the one sibling exempt from the rate limit (task_stop), which tells the agent when not to worry about throttling.

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