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

Annotations only declare the safety profile (not read-only, not destructive, not idempotent); the description adds the genuinely important behavior that the message is broadcast, not private, plus per-role pacing constraints. It does not cover failure modes (target not in room) or retry semantics despite exposing an idempotency_key, so it falls short of 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?

Two short sentences, front-loaded with purpose and immediately followed by the visibility constraint and the alternative. Dense but every clause earns its place; the parenthetical pacing figures are slightly redundant with the schema.

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 and a fully documented input schema, the description supplies what an agent needs: audience, visibility, and pacing. Missing only error/edge-case guidance (what happens if the named party is not in the room) and confirmation that the idempotency_key governs retries.

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%, so the baseline is 3. The description reinforces the 'by name' nature of `to` and repeats the length/pacing limits already documented in the `text` parameter, adding little the schema does not already say and nothing about `key`, `shadow`, or `idempotency_key` usage.

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 ('say something aloud'), specific resource/target ('to one person in your room, by name'), and an explicit scope statement ('everyone in the room sees and hears it') that separates it from whisper. An agent can distinguish this from the many sibling speech tools without opening a 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?

Names the alternative explicitly ('for private words, whisper') and gives the condition that selects it (public vs private). Also states the rate context ('lounge pace, one message every 10 seconds for a member, 30 for a shadow'), which governs whether the call is viable.

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