send_connection_request

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. This is a persistent, state-changing social action on LinkedIn — it creates a pending invitation that cannot be easily undone and may trigger rate limits or spam protections. The description reveals none of this: no mention of irreversibility, rate limits, prerequisites (auth), or limitations on daily connection requests. The dry_run parameter hints at the risk of actual action, but the description fails to explain 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?

The description is a single efficient sentence with no waste. However, it is arguably under-informative rather than concisely complete — it could add a sentence about dry_run or auth requirements without becoming verbose. Given the front-loaded, direct phrasing, it earns above-average marks.

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 persistent, rate-limited social action with no annotations and no output schema, the description is inadequate. It doesn't describe what happens on success/failure, the dry_run parameter semantics, auth dependency (visible from siblings but not stated), or any error conditions. With 3 parameters and 0% schema coverage, more explanation is needed for the agent to use this tool correctly and safely.

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 0%, meaning the description must compensate for the undocumented parameters. There are 3 parameters (note, dry_run, profile), and the description mentions 'optional note' but doesn't explain the dry_run parameter or the format/URL expectations of profile. The description adds some value by noting the note is optional, but leaves dry_run completely unexplained and doesn't clarify what 'profile' should contain (URL vs. ID). Overall, partial compensation for a high coverage gap.

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 'Send a connection request to a LinkedIn profile, with optional note' uses a specific verb+resource (send connection request to LinkedIn profile) and clearly states the scope. It differentiates from sibling tools like send_message and follow_person, as the action is distinct and well-named. The name itself is descriptive, and the description reinforces it without being a mere tautology.

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?

There is no guidance on when to use this tool versus alternatives. Given the large sibling set including send_message, follow_person, accept_invitation, and get_pending_invitations, the description doesn't clarify the distinction between sending a connection request and following someone or sending a message. No prerequisites (e.g., must be logged in) are stated, though sibling tools like linkedin_login and linkedin_auth_status hint at an auth dependency.

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