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

Annotations only declare it is a non-readonly, non-destructive, non-idempotent call; the description adds real behavioral rules beyond that — content constraints for summary (spoken prose, no markdown/URLs/code), a hard prohibition on secrets, bot_name stability across calls, and what the result means for delivery. It stops short of covering repeated-call/idempotency behavior, which matters for a non-idempotent tool that texts a human.

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?

A single dense paragraph with no waste and the core routing/lifecycle information front-loaded. It is slightly run-on, packing lifecycle, formatting, security and result handling into one block, but nearly every clause carries actionable content.

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 no output schema, the description usefully explains the delivery result ('if delivery.message is present, tell the user that sentence'), which covers the main return concern. Gaps remain: the full response shape on non-delivery, failure behavior for the error status, and any rate limits for a tool intended to be called on every task.

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, and the description genuinely adds meaning the schema lacks: 'Always use the same bot_name' (identity stability) and the summary style rules (plain sentences for speech, no markdown/URLs/code). It says less about the optional agent and detail parameters, which the schema already documents.

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?

'Report your progress to the user through Heard, which reads it aloud on their Mac or texts it to their phone' names a specific verb, resource and delivery mechanism. It is unmistakably distinct from the sibling inbox tools, which read/acknowledge messages rather than send progress updates.

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 cadence ('Call it on every task') and disambiguates each status value with a triggering condition: started on pickup, working at milestones not every step, needs_input when blocked, done, error. The 'not every step' exclusion is exactly the kind of when-not guidance that prevents over-calling.

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