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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond them: the tool returns procedural instructions (screens, buttons, fields) rather than data, and performs no action itself. The aside about JobDiva's REST API and lack of an official MCP server justifies the browser-automation route but is background rather than behavior of this call.

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 short sentences, front-loaded with the verb and the crucial caveat that nothing is opened, followed by the handoff. No redundant restatement of the title or annotations. The API aside is the only arguably expendable content but it is brief and supports the routing decision.

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?

With no parameters and no output schema, the description carries the burden of explaining what comes back, and it does: step-by-step JobDiva screens, buttons and fields, plus the pointer to the browser tools that execute. It stops short of saying what state the browser must already be in (session open, logged in) before the returned steps can be applied, which is the main remaining gap.

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 there is nothing for the description to disambiguate; schema coverage is 100% and the empty object is unambiguous. Baseline 4 applies for a 0-param tool.

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 name and first line state a specific verb+resource ('Find candidate'), and the description immediately corrects the likely misreading by saying it returns step-by-step JobDiva instructions and 'opens nothing by itself.' It also distinguishes itself from the cotlet_browser_* tools it hands off to. It does not distinguish itself from the very similarly named sibling jobdiva_search_candidates, which is the one confusion an agent is most likely to have.

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 clear follow-up instruction ('then do it with the cotlet_browser_* tools in the user's JobDiva Cloud Browser'), which tells the agent this is step one of a two-step flow. However, there is no explicit when-to-use-this-vs-alternative guidance against jobdiva_search_candidates — an agent seeing both names has to guess which one actually returns candidates.

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