say

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

With no annotations at all, the description carries the full burden and does disclose a genuinely non-obvious behavioral trait: delivery is pull-based and replies are not immediate. That is real value beyond any structured field. It omits auth/permission expectations and whether sending can fail, which keeps it from 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 units, front-loaded with the action and audience, then the crucial caveat. No filler sentences, and the warning is exactly the piece an agent most needs.

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 not be explained. For a one-param messaging tool the async delivery caveat covers the main risk of misuse. Minor gaps remain around peer differentiation ('send') and message content expectations.

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?

There is one parameter, 'text', with 0% schema description coverage, so the schema contributes nothing. The description does not clarify what 'text' should contain (plain text, formatting, length, whether addressee is needed), but the parameter is nearly self-evident from its name. A baseline 3 fits a single obvious param.

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 verb-plus-resource ('Message to the room') and names the audience ('the other agents and the human'), which is enough to distinguish it from read-side siblings like room/inbox. It does not, however, explain how it differs from the sibling 'send', which an agent may reasonably see as an overlapping write path.

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?

The description sets an important expectation ('Not a live chat... do not expect an immediate reply'), which shapes when an agent should prefer this versus a synchronous exchange. It stops short of naming alternatives (send, inbox, room) or stating when a message is warranted at all, so usage is inferred rather than specified.

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