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

Annotations already declare read-only, non-destructive, idempotent, closed-world, so the safety profile is covered. The description adds genuinely new behavior: the return value is procedural guidance (screens, buttons, fields), it performs no browser action itself, and the official JobDiva API is unusable without a JobDiva-issued client ID and there is no official MCP server. That last part justifies the indirect approach rather than restating annotations.

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 core behavior and the browser handoff are front-loaded, which is good. The closing API paragraph (759 paths across two versions, checked 23 Oct 2026) is informative but lengthy and the future-dated verification timestamp is noise that competes with the actionable instruction.

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 output schema, the description carries the burden of explaining what comes back, and it does: step-by-step screens, buttons, and fields. Combined with the browser handoff, an agent knows both what it gets and what to do next. Only the exact shape of the returned steps is left vague.

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. There is nothing further for the description to disambiguate, and the empty schema is consistent with the description.

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?

States a specific verb and resource (search jobs in the user's own JobDiva account) and immediately clarifies the tool does not itself search but returns step-by-step UI instructions. That reframing could momentarily read as inconsistent with the name 'search', but it resolves within the first sentence. Distinguishing from jobdiva_search_candidates is only implied by the resource noun.

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?

Explicitly tells the agent what to do with the result: execute the steps via cotlet_browser_* in the JobDiva Cloud Browser, and states the tool 'opens nothing by itself'. It does not name exclusion cases beyond that, and does not compare against sibling job-divination tools like jobdiva_find_candidate, so it stops short of full when/when-not coverage.

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