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

Annotations already cover read-only/safe/open-world, so the description wisely spends its space on non-annotation facts: results are read live from the caller's own account, ordering is newest-first, and the contents are third-party-authored and must be treated as data rather than instructions. That prompt-injection warning is genuinely useful behavioral context. Pagination depth and rate-limit behavior are left unstated, keeping it below a 5.

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?

Two sentences, zero waste, with the resource, ordering, returned fields, and downstream tool routing front-loaded. The safety note is the only trailing sentence and it earns its place.

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 compensates by enumerating the returned fields and ordering, so an agent knows what it gets back. Pagination is only implied via the schema's cursor parameter, and nothing is said about volume or expected size, so it is strong but not fully complete for a live-account listing tool.

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 100% and all six parameters (after, before, limit, cursor, unread, connectionId) are documented there, so the baseline is 3. The description adds only 'newest first' as an implicit hint about ordering and says nothing about the unread filter, date windows, or cursor reuse, so it does not go beyond the schema.

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 ('List your LinkedIn conversations') plus ordering ('newest first') and the exact fields returned (id, who it is with, unread count, last activity). An agent can distinguish this list-of-conversations tool from get_chat, list_chat_messages, or get_unibox without opening a schema.

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?

Gives clear downstream context: 'Use the id with list_chat_messages, send_chat_message and the other chat tools,' which tells the agent where this fits in a workflow. It stops short of naming when to prefer alternatives (e.g. find_cold_conversations, get_unibox, list_messages) or exclusions, so it is a clear context statement rather than full when/when-not guidance.

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