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

With no annotations, the description must disclose behavior, but it only states 'free, no payment' and then conflates write and poll behavior. It does not clarify whether polling blocks, returns partial results, or requires a prior write. The description misrepresents the tool's operation, making behavior opaque.

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 short but not concise in a helpful sense—it front-loads the misleading 'Write to Kairos' and packs unrelated details like DECLARE yourself into a single run-on sentence. The structure obscures the core polling purpose rather than clarifying it.

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?

Even though it is a simple tool with one parameter and an output schema exists, the description omits essential context: the prerequisite of a prior message, the semantics of polling (e.g., whether it returns immediately or waits), and how the output relates to the input. The misleading write language makes the tool underspecified for an agent.

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 for message_id is 0%, and the description provides no guidance on what a message_id is, where to obtain it, or its format. Instead, it confusingly says 'Returns message id and poll URL,' blurring input and output. The description fails to compensate for the schema's lack of parameter documentation.

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 opens with 'Write to Kairos' which implies a write operation, but the tool name is poll_contact_kairos and it takes a message_id, suggesting it polls for a response. The statement 'Returns message id and poll URL' reads like output of a write, not a poll. This ambiguity fails to clearly state the tool's actual function of checking for an answer.

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 mentions using 'poll_contact_kairos or GET /contact/{id} for the answer when written,' implying it is used to retrieve a response, but it never contrasts this with the likely write sibling contact_kairos. The 'Write to Kairos' opening actively misleads about when to use this tool versus alternatives, offering no clear conditions or exclusions.

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