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

Annotations already declare readOnlyHint=true and idempotentHint=true, and the description is consistent, explicitly promising it 'opens nothing by itself.' It adds useful context beyond the annotations: the return format (step-by-step screens, buttons, fields) and why the browser path is needed (Comeet grants API access at its sole discretion).

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 behavioral scope and the hand-off to cotlet_browser_* tools are front-loaded in the first sentence. The trailing note on Comeet's official API is somewhat tangential but earns its place by justifying why browser automation is the path.

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?

There is no output schema, so the description correctly explains what is returned (step-by-step instructions). It is still incomplete on one point: with no input parameters, an agent cannot tell how or where the rejection reason is supplied, which is central given the tool's name.

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?

With zero parameters the baseline is 4, and the description introduces no parameter confusion. The one caveat is that the name promises 'with reason' yet the schema accepts no reason argument, which the description does not explain.

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 states a specific verb and resource ('Reject candidate with reason in Comeet') and immediately clarifies the actual behavior: it 'Returns how to do it in Comeet step by step (screens, buttons, fields) and opens nothing by itself.' This correctly reframes the imperative-sounding name as a guide-retrieval tool, though it does not contrast itself with the sibling comeet_change_candidate_status.

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 gives a clear workflow: call this first for steps, then execute them with the cotlet_browser_* tools in the user's Comeet Cloud Browser. However, it offers no when-not guidance or comparison to alternative Comeet status-change tools, leaving the agent to infer that this is preferred over the API-based siblings.

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