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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description reinforces this with 'opens nothing by itself', resolving the apparent create-vs-read tension in the name. It adds genuine context beyond annotations by describing the return content (screens, buttons, fields) and by noting the API is only available on the top Manatal plan, which explains why browser automation is needed. It stops short of describing step format, length, or whether results are cached.

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 sentences, front-loaded with the core behavior and the no-side-effects guarantee before the follow-on tool instruction. The trailing note on official API plan availability is slightly tangential and carries an odd future-dated stamp ('checked 20 Oct 2026'), but it earns its place by justifying the browser route.

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 zero-parameter, read-only guidance tool with no output schema, the description covers what is returned at a high level, what does not happen, and what to do next. What remains missing is minor: the shape/granularity of the returned steps and whether callers should re-invoke per candidate.

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 tool takes zero parameters, so the baseline is 4 and there is nothing for the description to disambiguate. One small gap: it does not explain that no candidate details are supplied, leaving the agent to infer that the returned walkthrough is generic rather than tailored to a specific candidate.

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 concrete verb and outcome: it returns step-by-step instructions for creating a candidate in the user's own Manatal account rather than performing the write itself. It also names the follow-on tool family (cotlet_browser_*), which separates it from the mutation siblings like manatal_add_candidate_to_job. The only friction is that the tool name says 'create' while the body says it only returns guidance, requiring the agent to read past the name.

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?

Usage context is explicit: call this to get the screens/buttons/fields walkthrough, then execute it with the cotlet_browser_* tools in the Manatal Cloud Browser. There is no explicit when-not or statement of which sibling to prefer if an official-API path exists, but the two-step workflow is unambiguous.

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