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

Annotations already mark destructiveHint=true, and the description adds critical context: 'reaches a real person immediately and cannot be undone' and the integration requirement. This goes beyond the annotation and informs the agent of irreversible side effects and setup needs.

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 sentences, no fluff, action front-loaded, important caveats (irreversibility, integration requirement) included. Every sentence 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?

No output schema exists, so the description should explain what happens on success/failure, but it does not. Two of three parameters are undocumented, and the description does not clarify how to specify the prospect (via prospectId or linkedinUrl). The tool is incomplete for correct invocation.

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 only 33%, with only 'message' explained. The description elaborates on the 'message' parameter ('Pass the note you want sent, or omit it to use the saved draft') but provides zero clarification for prospectId and linkedinUrl, which are left entirely to the schema's bare names. The description fails to compensate for the low coverage.

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 states a specific verb ('send'), resource ('LinkedIn connection request'), and target ('prospect'), and clearly distinguishes it from siblings like draft_linkedin_message and send_email. It's unambiguous about what the tool accomplishes.

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 provides the prerequisite (LinkedIn connected in getcleed under Integrations) and implies it is for actual sending rather than drafting, but does not explicitly route the agent to alternatives like draft_linkedin_message for drafting. The 'cannot be undone' warning is helpful but not a usage guideline. No explicit when-to-use vs. when-not-to-use is given.

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