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

Goes well past the annotations (destructiveHint already flags irreversibility) by explaining why: it goes out immediately and cannot be unsent, with the specific remediation path. It discloses concrete per-account rate limits (30/day + 200/7d paid vs 20/day + 150/7d free), note-length ceilings, the 5-notes-per-30-days rule, and the distinct failure codes (linkedin_limit_reached, cannot_resend_yet, note_limit_reached).

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?

Front-loaded with the action and its irreversibility before the limits, which is the right ordering. The single dense paragraph packs a large amount of load-bearing detail (limits, error codes), but the limit enumeration and error-code list run long and would scan better as structure rather than prose.

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 destructive, open-world write with no output schema, the description supplies everything an agent needs: irreversibility, refund path via invitationId, refusal semantics, quota accounting, and an alternative for high-volume use. Nothing material is left to inference.

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 profileUrl, note, email, and connectionId are already documented in structured form. The description adds the account-tier constraint behind note length and the condition under which email is needed, but says nothing about connectionId (choosing which LinkedIn account to act from), which is the one parameter with real mis-selection risk. Baseline 3 is appropriate.

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 ('Send ONE LinkedIn connection invitation'), plus precise scope: from your own account, singular, immediate. It distinguishes itself from campaign-based inviting and from the related withdraw_invitation flow, so an agent can separate it from siblings like start_linkedin_connect or add_lead_to_campaign 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?

Explicitly says when not to use it ('To invite many people on a schedule, use a campaign instead') and names the follow-up path for reversal (withdraw_invitation with the returned invitationId). It also enumerates the refusal conditions (already_invited, in_campaign) and points to get_action_usage for remaining quota.

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