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

Annotations already declare readOnlyHint=true and destructiveHint=false, so safety is covered by structured data. The description still adds real behavioral context: the tool performs no browser action itself, its output is procedural instructions rather than data, and the official API requires a support-issued workspace key rather than self-serve credentials. The only shortfall is that it does not say what the returned steps look like structurally or what happens when no Cloud Browser session exists.

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 opening clause largely restates the title, and the essential fact — that this returns instructions rather than candidates — appears only after it. The trailing API-key aside is relevant prerequisites information but is stated in a dense, tangential run-on that competes with the primary workflow.

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, no-output-schema tool the description covers what is returned and how to follow up, which is close to sufficient. It leaves open how a specific job is targeted given there are no input parameters, and it provides no fallback path when the API key or Cloud Browser is unavailable.

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 with 100% schema coverage, so the baseline is 4 and the description is not obligated to explain inputs. It adds no parameter meaning, but none is needed for an empty 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 eventually clarifies that this tool does not return candidate data at all but instead returns step-by-step Recruiterflow navigation instructions ('screens, buttons, fields') and 'opens nothing by itself.' That is a specific and useful disclosure, but it directly conflicts with the name/title 'List job candidates', and the critical clarification is buried in the third clause. It also never distinguishes itself from the sibling recruiterflow_list_candidates or recruiterflow_get_job_pipeline, so an agent cannot tell which of the three to reach for.

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?

There is a concrete chained workflow: call this first, then execute with cotlet_browser_* tools in the user's Recruiterflow Cloud Browser. That is more than implied guidance. However, there is no when-not guidance and no comparison against near-identical siblings (recruiterflow_list_candidates, recruiterflow_get_job_pipeline) that would let an agent choose correctly.

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