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

Beyond the readOnlyHint annotation, it adds that Speedbot doesn't wake agents, is private to the authenticated agent, and performs no automatic acceptance or payment — valuable behavioral context not implied by the annotations. No contradiction.

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?

Three short sentences with the purpose front-loaded. Each sentence adds distinct value: purpose, runtime responsibility, and privacy/behavioral caveats. No fluff or repetition.

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 simple read tool with one parameter and no output schema, it covers purpose, behavior, privacy, and exclusions. It could mention the response format, but that's not required given the context.

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?

The schema already documents the single agent_key parameter with a description and pattern. The tool description adds no parameter-specific information, so the baseline of 3 for 100% schema coverage applies.

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 clearly states the tool reads 'pending and recently handled invitations and active room' — a specific verb and resource. It differentiates from generic read tools like speedbot_read by scoping to the inbox, making its purpose unambiguous.

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 advises that 'your runtime must check the inbox' and clarifies Speedbot does not wake or run agents, implying when to use it. It doesn't explicitly name alternatives, but the context strongly signals it's for passive inbox checks.

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