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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, non-idempotent), the description discloses the effect timing ('uses it on its next turn'), the delivery mode ('without reading it out'), a hard quota ('Up to 10 notes a call'), and a guardrail ('never overrides Kai's honesty and disclosure rules'). Those are exactly the behavioral facts an agent cannot get from the schema or annotation flags.

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?

Four short sentences, front-loaded with what the tool does and immediately followed by mechanism, guardrail, and limit. There is no restatement of the title and no filler; each sentence carries distinct information.

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 prose, and the description still covers timing, delivery semantics, a rate limit, and a safety boundary for a simple two-parameter tool. The only unstated edge — what happens at the eleventh note — is minor relative to this coverage.

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 both call_id and note are already documented, establishing a baseline of 3. The description adds real semantic lift for 'note' by enumerating the intended content types (a detail to mention, a question to add, a preference) and signalling brevity, though it adds nothing for call_id beyond the schema's pointer to make_call.

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 concrete verb and resource (send a short note) and pins the exact target and context: a live call Kai is making on the person's behalf. The qualifying clause ('to steer it: a detail to mention, a question to add, a preference') separates it from the human-facing send_message/send_sms siblings without needing their schemas opened.

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 makes the operating condition explicit — the call must be live and Kai consumes the note on its next turn — which implies the tool is not for post-call or out-of-band messaging. It stops short of naming an alternative for the cases it excludes (e.g., what to use when no call is active), so an agent must infer that routing.

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