list_conversations

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

With no annotations provided, the description carries full burden for behavioral disclosure. The phrase 'Open LinkedIn messaging' does communicate a physical browser action (navigation), which is useful context about side-effects (it changes the visible page state). However, it doesn't disclose whether this returns a list vs persists anything, page navigation side effects, or rate limits.

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 description is a single, compact sentence that front-loads the core purpose efficiently. Zero words are wasted. It loses a point only because it omits useful detail about the parameter and usage context that could fit in one or two additional short sentences.

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 tool with 1 optional parameter, no output schema, and no annotations, the description is thin. It doesn't explain the limit parameter, the return value shape, potential side effects of navigating the browser, or prerequisites like being logged in. Sibling tools like send_message and start_conversation exist in the same messaging domain, and the description doesn't clarify how results relate to them.

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?

Schema description coverage is 0%, and the description does not mention the 'limit' parameter at all beyond what the schema's min/max constraints imply. The description adds zero value about what 'limit' means, its default, or how it affects results. With 1 parameter and 0% coverage, the description should at least mention it.

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 'Open LinkedIn messaging and list visible conversation threads' clearly states a specific verb+resource (list conversations) and the action flow (open messaging first). It distinguishes itself from siblings like get_conversation (single thread) and start_conversation (create new). However, it could be more explicit about the differentiation from get_conversation.

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 no guidance about when to use this tool vs alternatives. The description implies opening the messaging tab first, which suggests a navigation prerequisite, but doesn't explicitly state it needs a prior login session or mention that start_conversation/get_conversation are the alternatives for specific thread operations. No exclusions or conditions are given.

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