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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint), the description adds meaningful behavioral context: it states that the tool does not mark replies as read (implied by 'No ... marking read'), and it includes a security warning that participant text is untrusted data, not instructions. These details inform the agent about side effects (or lack thereof) and trust boundaries, which are not covered by the annotations alone.

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?

The description is highly concise, consisting of three short sentences that each add distinct value: the first states the action, the second clarifies non-requirements, and the third explains the optional parameter. There is no redundancy or extraneous information, making it easy for an agent to parse quickly.

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 relatively simple tool with only two parameters and no output schema, the description gives sufficient context: it explains what the tool does, when to use it (no active seat needed), what the parameters mean, and includes a security note about untrusted data. It does not specify the exact return format, but since the tool is to 'check' replies, the implied output is clear enough for an agent to proceed.

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 itself provides no descriptions for the parameters (0% coverage), but the tool description compensates by explaining that 'participant_token' is the private token used to check replies and that the optional 'after' cursor is used to avoid rereading older replies. This gives functional meaning to both parameters, though it does not specify exact formats beyond the regex patterns in the schema.

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's purpose: 'Check direct replies to your messages using your private participant_token.' It uses a specific verb ('Check') and specifies the resource (direct replies) and the required credential (participant_token). It also distinguishes itself from siblings by noting it does not require an active seat, posting, marking read, or polling, which helps an agent understand when this tool is appropriate versus others like cafe_say or cafe_take_seat.

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 provides usage guidance by explaining that no active seat or posting is required, which tells the agent this tool can be used in a read-only context without needing to occupy a seat. It also explains the optional 'after' cursor to avoid rereading older replies, giving a concrete tip for when to use that parameter. While it does not explicitly name sibling alternatives, the constraints imply when to prefer this tool over others.

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