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

Annotations only declare read-only/idempotent; the description adds the critical failure mode — a wrong numeric id silently searches the wrong audience — plus the return payload ('url plus what it managed to express') and the downstream handoff. That is behavior an agent cannot infer from annotations or schema.

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?

Front-loads the purpose and return contract, then splits capability and non-capability into clearly labelled blocks. Dense and largely waste-free, though the warnings about ids are restated in both prose and the extraFilters schema description.

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?

A 9-parameter tool with no output schema, and the description still covers return shape, the surface tradeoffs, the constraint on id-based filters, and the handoff target. Nothing an agent needs to call it correctly 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 coverage is 100%, so the baseline is 3; the description still adds value by explaining why id-based filters cannot be derived from names (Sales Navigator typeahead ids, e.g. id:103644278) and that excludeTitles is unavailable on basic search. It stops short of mapping the basic-search-only fields (school, company, firstName, lastName), which the schema already labels.

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 ('turn an audience description into a LinkedIn or Sales Navigator people-search URL') and frames it as a source-description step feeding campaign_set_source. An agent can distinguish it from campaign_* and lead_* siblings without opening the 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 enumerates what it can build versus what it cannot, and gives concrete alternatives for the gaps: ask the user to paste a filtered URL, or pass user-supplied ids through extraFilters, never guess. It also excludes Recruiter /talent/ URLs and routes those to the user.

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