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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so safety is covered. The description adds substantial context beyond that: a concrete rate cap (3 MCP calls per minute), the real-time nature of the data, and the caveat that LinkedIn may omit message preview text.

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?

Three tightly packed sentences, front-loaded with purpose and the key field/return caveat before secondary details. Every sentence carries information, though it is dense enough that it approaches the limit of what is comfortably scannable.

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 describing return values and does so (chat_id, provider id, unread count, timestamp) while also disclosing the rate limit and the pagination caveat. Nothing an agent needs to call it correctly 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?

Schema coverage is 100%, so limit and cursor are fully documented in the schema. The description adds a note that profile_id is optional and defaults to the active profile, but adds nothing beyond the schema for limit/cursor, matching the baseline-3 case.

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 recent LinkedIn inbox conversations (chats) in real time') and enumerates the returned fields (chat_id, attendee provider id, unread count, timestamp). It clearly distinguishes itself from get_chat_messages by describing the latter as the way to read actual message content.

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 routes the agent: call get_chat_messages with the returned chat_id to read messages, and warns not to poll or walk every cursor page. It names the consuming siblings (get_chat_messages, reply_to_chat) and states the condition that selects them.

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