Search institutions by name (partial match). Page-paginated. Use to discover an institution's inst_ id or normalized_name. (Costs 10 Zooq credits.)
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Institution name (min 3 chars). | |
| page | No | Page number, >=1 (default 1). | |
| limit | No | Results per page, 1-50 (default 20). |
| Name | Required | Description | Default |
|---|---|---|---|
| items | No | Array in the example |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover read-only, idempotent, non-destructive behavior. The description adds useful behavioral context: partial-match search, pagination behavior, and a 10-credit cost. This meaningfully supplements the annotation-only safety profile.
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 short sentences, each adding distinct information: what it searches, how results are paged, what to use it for, and cost. No filler or repetition of schema details.
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 a simple search tool with fully documented parameters, rich annotations, and an output schema, the description covers what an agent needs: query behavior, pagination, intended use, and cost. Nothing critical 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 description coverage is 100%, so the baseline is 3. The description adds value by clarifying that name performs a partial match and that results are page-paginated, which is not fully evident from the parameter names alone.
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 clear action and resource: search institutions by name with partial matching. It also names the intended outcome, discovering an institution's inst_id or normalized_name, which separates it from people, company, job, and post search tools.
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?
Provides explicit context for when to use the tool: to discover an institution's inst_id or normalized_name. It does not explicitly name sibling alternatives or when not to use it, but the use case is clear enough for an agent to select it appropriately.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools are separated by domain prefixes and the descriptions are unusually explicit about differences, but there are direct overlaps: companies_name_lookup is the same upstream as search_companies, companies_entity_id vs companies_universal_name_to_id resolve different id spaces, and search_people/search_people_live plus search_companies/search_companies_live cover similar ground. An agent can usually pick correctly, but only after close reading.
The set is consistently snake_case with readable domain prefixes like companies_, jobs_, posts_, profile_, and search_. Deviations include the unexplained g_* prefix, jobs_details_v2's version suffix, affiliate_program lacking a resource prefix, and the duplicate naming convention of companies_name_lookup vs search_companies.
45 tools is well above the 25+ threshold and creates a heavy surface for an agent to scan. While the domains are broad, some tools are redundant (companies_name_lookup/search_companies) or tangential (affiliate_program), so the count is not fully justified.
The server covers people, companies, jobs, posts, email, schools, and skills with both search and detail endpoints, which is strong for a read-only LinkedIn API. Obvious gaps like a global post search or a company followers list are absent, but the existing paths support most workflows without dead ends.