Search LinkedIn Jobs

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description adds valuable behavioral context by mentioning it hydrates LinkedIn's virtualized result cards, deduplicates results, and returns a cursor page, which are not obvious from the 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?

The description is a single long sentence with a dense list of filters. It front-loads the core purpose but becomes somewhat unwieldy. It could be better structured by separating the action from the parameter list, yet it remains readable and informative.

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?

Given the tool's complexity (nested filters, pagination, many enums), the description covers the essential workflow: searching visible pages, applying filters, hydrating cards, and returning a paginated deduplicated page. The existence of an output schema reduces the need to describe return values. It misses some details like session dependencies, but annotations and schema fill in much of the gap.

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 low (22%), so the description should compensate. It names many filter categories (keywords, location, Date posted, sorting, etc.) and clarifies certain parameters like 'typed location' and 'Date posted' mapping to location and freshness_hours, but it does not explain cursor, page_size, context_id, request_id, or detailed semantics for each filter. Partial compensation, not full.

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 clearly states the tool searches LinkedIn Jobs pages with a specific verb ('Search') and resource ('LinkedIn Jobs'). It lists numerous filter categories and notes it returns a deduplicated cursor page, distinguishing it from other tools like linkedin.jobs.get or linkedin.people.search by scope and behavior.

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 description implies usage (searching jobs with optional filters) but provides no explicit guidance on when to use this instead of alternatives, no exclusions, and no mention of prerequisites or session requirements. The sibling tools like linkedin.jobs.get signal a complementary role, but the description does not state this relationship.

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