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

Annotations cover the safety profile (readOnly=false, idempotent=true, destructive=false, openWorld=false), and the description adds genuinely new behavioral context: claims must derive from a stored search result and remain unverified research rather than profile facts. That provenance/verification framing is not available in any structured field.

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?

Three dense sentences, front-loaded with the core action and constraints. No filler, though the final sentence about proposals sits slightly apart from the earlier provenance rule.

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?

An output schema exists so return values need not be described, and annotations carry the safety profile. The remaining provenance and verification semantics are covered, leaving only the relationship to the retrieval sibling unstated.

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 0%, so the description carries the burden. It compensates well by explaining the six-claim cap, the claim field set (role/company/location/website/bio), the citation requirement, and the abstain path that leaves linkedin_url absent, mapping directly onto the three parameters.

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: 'Submit one retrieved LinkedIn candidate, or abstain' with cited observations. It clearly distinguishes the submission act from a retrieval/search act, though it does not explicitly name the sibling that retrieves candidates (search_enrichment_web).

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 phrase 'or abstain' implies a conditional when-not path, and the provenance rule hints at when a submission is valid. However, no alternative sibling (search_enrichment_web, enrich_person, enrichment_batch_status) is named for routing, so usage is only implied.

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