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

Annotations already indicate a mutating, destructive operation, so the description does not need to restate that. It adds value by disclosing that Sales Navigator and Recruiter have specific subject/signature requirements, which is behavioral context beyond the annotation flags. No contradiction with annotations is present.

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 with no fluff. It front-loads the core purpose and packs in the key operational steps (resolve users, get inbox) and product-specific nuances efficiently.

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 complex tool with 7 parameters, nested objects, and no output schema, the description is relatively brief. It covers the main flow but omits details on return values, error conditions, or the semantics of optional parameters like 'name' and 'attachments.' It provides a functional overview but not complete coverage for an agent to use all parameters confidently.

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 low (43%), and the description partially compensates by explaining that inbox_id comes from linkedin_list_inboxes and users_ids must be resolved. It also mentions specifics for subject/signature. However, it does not clarify the 'text' or 'name' parameters, nor does it detail the attachments structure, leaving gaps given the low schema coverage.

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 states a specific verb ('Start') and resource ('conversation') with the key qualifier 'from an explicit inbox,' which distinguishes it from sibling tools like linkedin_start_conversation. It also mentions the supported product types (Classic, Sales Navigator, Recruiter) and capabilities (one-to-one, group, attachments), making the purpose immediately clear.

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 explicit prerequisites: resolve recipient user IDs and obtain inbox_id via linkedin_list_inboxes. It also gives product-specific guidance (Sales Navigator requires subject, Recruiter may require subject and signature). However, it does not explicitly contrast with linkedin_start_conversation or state when to use this tool instead, so it lacks a clear exclusion clause.

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