Browse industry verticals; sort by provider/API count.
| Name | Required | Description | Default |
|---|---|---|---|
| q | No | ||
| page | No | ||
| sort | No | ||
| limit | No | ||
| context | No | Optional: why you are asking. One sentence — the task you are trying to complete, or what you expect to get back. Never included in the answer and never used to rank; it is read only when a result turns out to be wrong, which is when knowing the intent is what makes the report actionable. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description carries the full burden of behavioral disclosure. It communicates only that the tool browses and sorts by count; it does not reveal pagination behavior (implied by page/limit params), whether q filters results, what 'provider/API count' means, or what the return payload looks like. Browsing implies read-only, which is some signal, but coverage is thin given zero annotation support.
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?
One short sentence plus a fragment, front-loaded with the core action and the distinctive sort affordance. No wasted words. It is efficient, though it could absorb a little more useful detail (e.g., what q filters) without becoming bloated.
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?
With no output schema, no annotations, and only 20% schema coverage, the description is the only behavioral source, and it is too thin. An agent has no idea what q accepts, which sort values are legal, how pagination works despite page/limit defaults, or what shape the result takes. For a 5-parameter discovery tool this is a meaningful completeness 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 coverage is only 20% (just the 'context' parameter is described), so the description must compensate. It does clarify 'sort' by stating the sort dimension is provider/API count, but it does not enumerate valid sort values, and the 'q' parameter's filtering semantics are left entirely unexplained. page/limit are partially self-documenting via numeric names and defaults, yet the overall parameter picture remains largely opaque.
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 clear resource (industry verticals) and a concrete capability (browse, sort by provider/API count). Among the large find_* family it is reasonably distinguishable from get_industry and get_industry_leaders by framing itself as a listing/discovery tool, though it never states how it differs from those siblings.
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 verb 'browse' and the sort capability imply discovery use, but the description gives no explicit when-to-use guidance, names no alternatives (find_areas, find_regions, find_tags, find_cohorts all compete for the same browse job), and offers no exclusions or conditions for selecting this tool over its many siblings.
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 clearly separated by artifact type or resource (find_mcp vs find_openapi vs get_provider vs get_api), but the sheer volume creates some genuinely confusable clusters: apis_io_search vs find_apis vs find_artifacts, and insights_adoption vs insights_dimensions vs find_company_insights. Several readiness-related tools (what_can_i_fix, simulate_fixes, readiness_gates) also share a conceptual boundary, though their descriptions do help.
The dominant patterns (find_*, get_*, cohort_*, compare_*) are consistent and predictable, but the set mixes in irregular names like apis_io_search, tag_group_tags, what_can_i_fix, whats_changed, and resolve. These deviations are readable but break the otherwise regular verb_noun convention.
106 tools is far beyond the typical well-scoped server and will impose a heavy selection burden on agents. The server covers a genuinely broad domain (catalog search, ratings, cohorts, agent readiness, lists, exports, feedback), so the count is defensible in scope, but it is still too many to navigate efficiently.
The surface is remarkably complete: search and browse, single-entity detail, comparisons, cohort analytics, agent-readiness assessment, saved searches, list management, feedback/correction flows, and full dataset exports are all covered. There are no obvious dead ends, and even minor operations like re-running saved searches or simulating fixes are present.
