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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), and the description adds genuinely non-annotated context: it consumes the daily messages quota and requires a premium/InMail path for out-of-network recipients. It does not discuss failure modes or what happens if the quota is exhausted, which keeps it short of a 5.

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 first two sentences restate the same conversation_linkedin_id/recipient_linkedin_id rule in slightly different words, which is redundant filler. The quota and alternative-tool guidance is well placed and front-loaded, but the definition could shed roughly a sentence without losing information.

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?

With an output schema present, return values need no explanation, and the annotation set plus the idempotency_key schema field covers safety and retry semantics. The description rounds this out with quota impact and sibling routing, leaving little an agent needs that is missing.

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 100%, so the baseline is 3, but the description adds a cross-parameter decision rule the schema alone only implies: conversation_linkedin_id for replies in an existing thread vs recipient_linkedin_id for initiating a new conversation. That routing guidance is meaningful value on top of the field-level docs.

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+resource ('Send a LinkedIn DM via Voyager createMessage') and immediately differentiates itself from the Sales Navigator variant and the bulk job path. An agent can identify this as the classic-inbox one-off send without opening any 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 routes between the two id parameters (existing thread vs new DM), states eligibility for the new-DM path (1st-degree connections or InMail), and names two alternatives with their selecting conditions: salesnav_send_message for Sales Navigator threads, create_job for more than ten messages. This is textbook when-to-use/when-not.

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