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

Annotations already declare read-only/idempotent behavior, and the description adds meaningful workflow context: this is a pre-action resolution step, multiple plausible results must be disambiguated before any write, and the output is a stable system ID commonly in ACo... format. This goes beyond the annotation flags and helps prevent unsafe or premature actions.

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?

Most sentences are front-loaded and purposeful: purpose, trigger conditions, disambiguation policy, ID format, and anti-patterns all earn their place. The ID-obtaining chain is dense but relevant; a little restructuring or bullet formatting would make it easier to scan.

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?

Together with annotations and schema, the description covers input semantics, safety, disambiguation, and output ID format. It doesn't specify no-match behavior or output shape, but the absence of an output schema is partially mitigated by the stable-ID explanation. Adequate for a resolver tool of this complexity.

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 covers filters and account_id, while the description compensates for the under-documented keywords parameter by specifying accepted content (name, role, employer, location keywords) and by listing how to obtain the stable ID and what never to pass instead. The limit parameter remains only partially addressed, but its schema constraints make its meaning clear enough.

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 opens with a specific verb and resource: 'Resolve a human description ... to LinkedIn people and their stable system IDs.' It clearly distinguishes itself from siblings like linkedin_resolve_company by targeting people and by framing the input as a natural-language description rather than an ID.

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?

It gives concrete trigger examples ('message Sarah at Acme', 'connect with the CTO of X') and an explicit exclusion ('rather than providing an ID'). It also instructs the agent to disambiguate before writes, but it doesn't name the direct-ID alternative tools as replacements, so it is clear context without a full when-not/alternative matrix.

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