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

Goes well beyond the annotations by disclosing the irreversible side effect ('goes out on LinkedIn immediately and cannot be unsent'), the credit cost of an InMail and the need to confirm with the user, the already_inmailed refusal with no credit consumed, the campaignNote in the response, and the two separate daily allowances (40 InMail, 100 message). This is consistent with destructiveHint=true rather than contradicting it; only the return shape is left thin, which is expected with no output schema.

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 purpose and the send_message contrast before any of the conditional detail, and nearly every sentence carries operational information (credits, refusals, allowances). It is a single dense block, though; the refusal, credit, and rate-limit clauses would scan better as separate lines.

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 14-parameter, nested-object mutation with destructive semantics and no output schema, the description covers the things an agent could get wrong: irreversibility, credit consumption and user confirmation, product-seat requirements, id prerequisites for the special recipient types, and the rate limits. Remaining gaps (attachment and video/voice parameters) are fully self-documented in the schema.

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 the baseline is 3, but the description adds meaning the schema does not: the interaction between the inmail flag and the via enum determines which allowance is consumed, and that an InMail within an existing campaign is rejected. It does not add anything for the recruiter/attachment/video/voice parameters beyond what the schema already documents.

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 ('Start a NEW LinkedIn conversation from your own account, now') and immediately distinguishes itself from the sibling send_message by enumerating the exact cases it covers (InMail to a non-connection, Sales Navigator/Recruiter, group conversation, company page, job applicant, unanswered invitation). An agent can pick between this and send_message without opening either 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 names the alternative (send_message) and the condition that routes here ('the cases send_message does not cover'), and names the prerequisite lookups for each variant: get_inmail_credits, list_job_applicants, list_received_invitations. It also gives a when-not rule: an InMail to someone already InMailed by a campaign is refused.

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