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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and openWorldHint=false; the description adds the critical behavior that the tool performs no LinkedIn action itself and only returns procedural guidance, which an agent could not infer from annotations. The note that LinkedIn's official API requires an approved application explains why the browser path exists. Missing details are minor (no mention of whether a Cloud Browser session must already be open).

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 disclosure is front-loaded, but the middle sentence is a tangled semicolon splice mixing what it returns, what it does not do, and the follow-up tools. 'from ChatGPT, Claude or any AI agent' is marketing filler, and the parenthetical '(checked 6 Nov 2026)' adds little for tool selection.

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, no output schema and rich annotations, the description carries the right burden: what the tool returns, that it takes no action, and which tool family completes the task. It could be stronger by naming the prerequisites for the Cloud Browser session, but nothing essential for correct invocation is missing.

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?

Zero parameters, so there is no schema semantics to compensate for; baseline 4 applies. The description adds the useful implication that no company-name query is passed here, which prevents an agent from expecting filter arguments.

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 makes clear this is not a real search endpoint: it 'Returns how to do it in LinkedIn step by step (screens, buttons, fields) and opens nothing by itself', which is a specific and unusual verb+output. The name 'linkedin_search_companies' slightly overpromises an executed search, but the description corrects that immediately and distinguishes it from the cotlet_browser_* siblings that actually perform the work.

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 states the usage path explicitly: call this first to get instructions, then carry them out with the cotlet_browser_* tools in the user's LinkedIn Cloud Browser. It does not cover when to prefer cotlet_app_guide or why to choose this over linkedin_search_people, but the primary sequencing guidance is clear.

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