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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false. The description adds meaningful context beyond that: it says the tool 'opens nothing by itself' (it returns instructions, not results) and explains that the official LinkedIn API mostly requires an approved application, justifying the browser-based approach. Return format is described at a high level ('step by step (screens, buttons, fields)') but not in detail.

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 message (returns instructions; execute with browser tools) is front-loaded and clear, but the text is padded with audience marketing ('from ChatGPT, Claude or any AI agent') and a date-stamped aside about LinkedIn's official API ('checked 6 Nov 2026') that does not change how the agent calls the tool. Trimming those two clauses would leave a tighter, sharper definition.

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 guide tool with full annotation coverage, the description supplies the essential missing context: what the return value actually is (procedural guidance, not conversation data), that the tool itself has no side effects, and which sibling tools carry out the plan. The remaining gap is modest: it does not describe how granular the returned steps are or whether the agent should fetch app-guide context first.

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 per the calibration baseline a 4 is appropriate. There are no parameter semantics the description needs to compensate for, and it introduces no confusing parameter claims.

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 names a specific resource (the user's own LinkedIn conversations) and, crucially, discloses that the tool returns step-by-step instructions (screens, buttons, fields) rather than the conversations themselves. It distinguishes itself from the cotlet_browser_* siblings, which perform the actual actions. The opening phrase 'Read conversations' is a bit misleading at first glance since the tool does not read anything, which keeps it from a 5.

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?

The description clearly routes the agent: call this to get the procedure, then execute it with the cotlet_browser_* tools in the user's LinkedIn Cloud Browser. It does not explicitly state when not to use this versus sibling LinkedIn action tools, but for a read-oriented guide tool the follow-on path is unambiguous.

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