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

Annotations already cover safety (readOnlyHint, destructiveHint), but the description adds useful non-schema context: 'public' profiles only, 'one per call,' 'no limit field,' and that email addresses are not returned. This enriches understanding beyond what annotations provide.

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?

Two sentences, front-loaded with the key action and scope. The second sentence lists many return fields, which is informative but somewhat verbose; however, every element is relevant to understanding the output.

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 no output schema, the description compensates by enumerating returned fields (name, headline, experience, education, etc.). It also notes email exclusion. The only missing element is explicit guidance on failure modes or rate limits for a non-idempotent, open-world 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?

The schema description for 'query' (100% coverage) already describes acceptable formats. The description repeats this but adds the concrete username example 'jane-example' and clarifies that a limit field is absent, which slightly exceeds the schema but is largely redundant.

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?

Strong, specific verb+resource: 'Look up one public LinkedIn profile per call.' Distinguishes itself from the sibling 'linkedin-jobs' by focusing on profiles rather than job listings, and the scope notes (one profile per call, public only) add precision.

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?

Implies correct usage with 'Pass {query} as a username, profile URL or URN; there is no limit field,' which tells the caller what to supply. However, it doesn't explicitly name or exclude alternatives like a hypothetical 'linkedin-search' sibling or explain when looking up en masse would be inappropriate.

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