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?
The description adds meaningful behavioral context beyond the annotations: partial-match semantics, pagination, and the 10 Zooq credit cost. The annotations already declare readOnly, idempotent, open-world, and non-destructive behavior, and the description supplements rather than contradicts them.
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?
Two short sentences plus a parenthetical cost note. The main behavior and use case are front-loaded, and every element earns its place without filler or repetition.
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, paginated search tool, the description covers purpose, matching behavior, pagination, cost, and intended outcome. The presence of an output schema means return-value details are already handled, so nothing essential 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?
The schema already describes all three parameters with full coverage, so the description does not need to restate them. It does add context like partial-match behavior and pagination, but this is general behavior rather than parameter-specific semantics.
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?
Clear verb and resource: 'Search institutions by name (partial match)' immediately identifies what the tool does and its scope. The mention of discovering an institution's inst_id or normalized_name distinguishes it from the other search_* sibling 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?
The description states a concrete use case: 'Use to discover an institution's inst_id or normalized_name.' It does not explicitly name alternatives or exclusions, but the purpose is specific enough to guide selection among the large sibling set.
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.
Many tools have strongly overlapping purposes: companies_name_lookup is explicitly equivalent to search_companies, companies_enrich/companies_info/companies_universal_name_to_id all return company-profile data, and profile_full overlaps with profile_employment_history and profile_enrich. The descriptions are detailed, but an agent would still frequently have to choose between near-duplicate endpoints.
Tool names mostly follow a predictable resource-prefixed snake_case pattern, such as companies_*, jobs_*, posts_*, profile_*, and search_*, which makes the set readable and groupable. Minor inconsistencies like jobs_details_v2, g_title_skills_lookup, and mixed noun suffixes (info/details/full/lookup) keep it from a perfect score.
44 tools is well beyond the heavy 25+ band, and several tools appear to be different lookup modes or near-duplicates of the same underlying capability. The broad LinkedIn-style data domain explains much of the size, but the set still feels bloated rather than well-scoped.
The API covers the core read-only professional-data workflows well: people, companies, jobs, posts, comments, likes, email discovery/verification, schools, skills, and targeted searches. Minor gaps exist, such as some job filters being unusable and no direct exposure of certain profile alias endpoints, but agents can generally complete end-to-end workflows.