Skip to main content
Glama
Sign In

apis-io

by io.apis
OverviewDiscussionsAdmin

find_cohorts

Read-only

START HERE for market-level questions. Every scored population of providers in the catalog — tags, industries, regions, areas and VC portfolios — as one browsable index. Filter by kind, minimum population, or promotion tier (report/brief/data). Then call cohort_stats for the distribution, cohort_rankings for the leaderboard. Priced per result — $0.005 per request plus $0.0002 per record returned (less past 100), capped at $0.50 a request, under pay-as-you-go; included in Understanding and Influence. Estimate first at /api/v1/prices/estimate. See apis://prices.

Input Schema

NameRequiredDescriptionDefault
qNoSubstring match on cohort name or slug.
kindNoRestrict to one roster source.
pageNoPage number, 1-based (default 1).
tierNoPromotion tier: report (100+, report-grade), brief (25+), data (everything else).
limitNoResults per page, 1-100 (default 25).
contextNoOptional: one sentence on why you are asking. Never used to rank; read only if a result is wrong.
min_providersNoOnly cohorts with at least this many providers. 25+ is brief-grade, 100+ report-grade.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / context / description
      Previous value: -"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."New value: +"Optional: one sentence on why you are asking. Never used to rank; read only if a result is wrong."
    • changedInput schema / properties / page / description
      Previous value: -"Page number, 1-based (default 1). Use with `limit` to walk a long list."New value: +"Page number, 1-based (default 1)."
  2. Changed2 schema fields changed
    • addedInput schema / properties / limit / description
      Added value: +"Results per page, 1-100 (default 25)."
    • addedInput schema / properties / page / description
      Added value: +"Page number, 1-based (default 1). Use with `limit` to walk a long list."
  3. Changed1 schema field changed
    • addedInput schema / properties / context
      Added value: +{
+  "description": "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.",
+  "type": "string"
+}
  4. Added

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already establish readOnlyHint and openWorldHint, so the safety profile is covered. The description adds genuinely useful operational context beyond that: the full pricing model with per-record and per-request rates, the $0.50 cap, plan inclusion, and a pointer to /api/v1/prices/estimate and apis://prices. It does not describe result shape or pagination behavior, but pricing transparency is a real addition.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the highest-value instruction ('START HERE'), followed by scope, routing, and cost. Dense but well ordered. The pricing sentence is long, though it is bounded by a pointer to apis://prices, so it earns most of its length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 7-parameter discovery tool with no output schema, the description covers purpose, scope, routing to downstream tools, and cost — enough to call it correctly. The one real gap is that return shape/pagination is not hinted at, though the sibling routing partially compensates.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter including the tier and kind enums, page/limit ranges, and min_providers semantics is already documented in the schema. The description groups the filter axes (kind, minimum population, promotion tier) but adds no format or behavioral detail beyond what the schema states, making the baseline 3 appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (find) and resource (cohorts), and defines the resource precisely as 'every scored population of providers' spanning tags, industries, regions, areas and VC portfolios. It also distinguishes itself from the many sibling find_* tools by positioning itself as the unified index rather than a single-roster lookup.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Opens with 'START HERE for market-level questions' and explicitly routes the agent onward: cohort_stats for distributions, cohort_rankings for leaderboards. It also names the filtering dimensions, so an agent knows both when to pick this tool and how to move on from it.

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

All apis-io toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources