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

Annotations already declare readOnlyHint/ idempotent/ non-destructive, so the safety profile is covered. The description adds genuine context beyond them: it requires the user's own Sales Navigator-capable account (an auth prerequisite) and states a capability boundary, 'cannot save searches or custom filters,' which corroborates the forbidden save_* parameters in the 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?

Four tight sentences, front-loaded with purpose, then usage, then the helper-tool dependency, then the limitation. The filter enumeration is slightly list-heavy but every clause carries operational value; nothing is padding.

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 an open-world search tool with an opaque schema and no output schema, the description covers purpose, eligible filter dimensions, the filter-name resolution dependency, and the inability to persist searches. It does not address result volume or pagination behavior, which is a minor gap given no output schema exists to document returns.

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?

Only account_id carries a schema description (reported coverage 33%), while save_search/save_custom_filter are schema-forbidden and the actual filter payload is free-form via additionalProperties. The description compensates by listing the meaningful filter categories and pointing to linkedin_get_search_parameters(product='sales_navigator') to translate human filter names into IDs, which is real information the opaque schema does not supply.

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 names a specific verb and resource tied to a distinct product surface (Sales Navigator people search) and enumerates the advanced filter dimensions (lead lists, seniority, years of experience, company, geography, function) that separate it from generic people search. It stops short of explicitly naming the sibling tools it is not (linkedin_search_people, linkedin_recruiter_search_people), so the agent must infer the boundary from 'advanced prospecting intent'.

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 states a clear when-to-use condition ('Use for advanced prospecting intent such as lead lists, seniority, years of experience...') and gives a concrete prerequisite action for filter resolution. There is no explicit when-not guidance or named alternative sibling, but the context is unambiguous for this capability.

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