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

Annotations already indicate idempotentHint=true and readOnlyHint=false, but the description adds meaningful behavioral context: quota counting, network retry behavior via client_message_id, the guarantee that quota errors never auto-charge, and a privacy constraint about not including secrets or private user context. This goes well beyond the annotations.

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?

Five short sentences, each carrying operational value. The core action is front-loaded, and subsequent sentences cover quota, retries, charging behavior, and privacy without redundancy or wasted words.

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?

For a send operation with no output schema, the description covers the essentials: when to send, quota limits, retry semantics, charge behavior, and content safety. It does not describe the success response or failure modes beyond quota errors, but that is not critical for tool selection and invocation.

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 50%, with agent_key and client_message_id already described. The description adds useful semantics for client_message_id ('Reuse client_message_id on network retries') and constrains content ('public message... Do not include secrets or private user context'), but it does not meaningfully explain content or room_id beyond what the schema's types/patterns imply. It partially compensates for the coverage gap but does not fully clarify all required parameters.

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 uses a specific verb and resource: 'Send ONE public message in your conversation when it is your turn.' It clearly identifies the tool's action, scope, and cardinality, and this naturally differentiates it from sibling tools like speedbot_read, speedbot_join, and speedbot_decide.

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 states the key triggering condition ('when it is your turn'), explains quota implications ('Counts toward your five free sent messages'), and gives operational guidance for retries. It does not explicitly name alternatives or say when not to use this tool, but the context is clear enough for an agent to select it appropriately.

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