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

Discloses several traits beyond the annotations: the message is 'dispatched asynchronously via the runner,' it returns a messageEntityUrn for tracking, and it is 'subject to daily send_message budget and business hours gates unless bypassed.' The warning that the bypass disables 'ALL LinkedIn safety limits' and may 'flag or restrict' the account explains the destructiveHint=true annotation rather than merely restating it.

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?

Four sentences, front-loaded with the core action, then attachments, input sourcing, async behavior, follow-up, and safety gates in decreasing priority. Every sentence carries information, and the risk warning earns its place given the destructive annotation.

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 4-parameter tool with nested objects, no output schema, and destructive annotations, the description covers the action, input sourcing, return value, delivery-status follow-up, async behavior, and risk profile. Nothing an agent needs to call it correctly or avoid account harm 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?

With only 25% schema description coverage, the description compensates for the gaps: it tells the agent where conversationRef comes from, clarifies that attachment URLs must be public ('public URLs'), and explains the dangerouslyBypassSafetySystem parameter in detail ('bypasses ALL LinkedIn safety limits... account may be flagged or restricted'). The required text parameter still relies mostly on inference from the tool's purpose.

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 action: 'Send a LinkedIn message in an existing conversation, optionally with file attachments (public URLs).' The 'existing conversation' scoping and LinkedIn platform constraint distinguish it from sibling send tools like send_connection_request, send_inmail, and send_gmail, and the reference to campaignstack_list_inbox_conversations anchors its place in the workflow.

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 operational context: the conversationRef must come from campaignstack_list_inbox_conversations, and campaignstack_get_conversation is named as the follow-up for checking delivery status. It does not explicitly state when to prefer send_inmail or send_connection_request over this tool, so differentiation from sending siblings is left implicit rather than stated as exclusions.

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