Prepare LinkedIn Connection Invitation

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

The description adds valuable behavioral context beyond the annotations: the draft is 'immutable', and the output is 'the exact client-approval preview'. It also reinforces the non-sending nature. With annotations already indicating idempotent and non-destructive, these additions are meaningful and do not contradict the annotations.

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 two sentences, front-loaded with purpose and critical exclusions. Every clause earns its place: 'Inspect one exact visible profile' establishes scope, 'immutable invitation draft' sets expectations, 'does not send' is a crucial differentiator, and the note length and preview mention are concise and useful.

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?

Given the prepare/execute pattern and the presence of an output schema, the description covers the essential aspects: it says what it inspects, what it creates, what it does not do, and what the output will be ('client-approval preview'). It does not mention prerequisites beyond visibility, but the sibling list and clear naming fill some gaps. Overall, it is complete for this moderately complex tool.

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 0% schema description coverage, the description must explain all parameters. It only hints at 'note' (optional personalized note with 200-char limit) and 'profile' (visible profile), but leaves context_id and request_id entirely unexplained. The schema provides only titles and constraints, no descriptions, so the description fails to compensate for the 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 clearly identifies the action as preparing (not sending) a LinkedIn connection invitation. It distinguishes itself from the sibling 'linkedin.invitations.send.execute' by explicitly stating 'This does not send the invitation.' The verb 'create' and resource 'invitation draft' are specific and unambiguous.

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 clear context: it operates on 'one exact visible profile' and produces a draft for later approval. It explicitly excludes sending ('does not send the invitation'), which differentiates it from the execute tool. However, it does not explicitly name alternatives or state when to prefer this tool over others.

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