apis-io

find_operations

UNDERSTANDING — CATALOG-WIDE operation search: which providers expose a path matching your terms. "Who has a POST /refunds" had no answer before this — tags are what a company says about itself, a path is what its API accepts. Terms match path SEGMENTS (all must appear), so q="payment intents" finds /payments/v1/intents. Add method to narrow by verb, deprecated=true for the retiring ones. One row per real operation: a provider's spec is split per tag, so the same call can live in several of its documents, and apis lists them all. Reads matching providers' surfaces up to max_providers (cap 100) and tells you in meta.query.truncated when more matched than were read.

Input Schema

TableJSON Schema

Name	Required	Description
`q`	Yes	Path words, all of which must appear, e.g. "refunds" or "payment intents".
`page`	No
`limit`	No
`method`	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.
`deprecated`	No	Only operations the provider marked deprecated.
`max_providers`	No	How many matching providers to read (default 40, cap 100).

TDQS

A4.7/5.0

Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses segment-wise matching, per-operation row semantics despite tag-split specs, the `apis` aggregation of duplicate documents, max_providers cap behavior, and the `meta.query.truncated` signal. This goes well beyond a minimal definition.

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?

The description is dense and front-loaded with the core purpose, and most sentences add operational value. The 'tags are what a company says about itself' aside is helpful for differentiation but slightly rhetorical; overall it remains well-structured for a tool with this nuance.

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

Completeness5/5

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

Given seven parameters, no output schema, and no annotations, the description covers query semantics, filters, duplicate handling, provider limits, and truncation metadata. Nothing essential for correct invocation is missing.

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

Parameters5/5

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

Schema coverage is 57%, but the description meaningfully enriches the key parameters: it explains q as path segments that all must appear, method as a verb narrow, deprecated as targeting retiring operations, and max_providers as the read cap with truncation reporting. This compensates for the incomplete schema and adds real selection guidance.

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?

The description opens with a specific, differentiated purpose: 'CATALOG-WIDE operation search: which providers expose a path matching your terms.' It names the resource (operations), the verb (search/find), and draws a clear contrast with tags, so an agent can distinguish it from find_tags/find_providers.

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

Usage Guidelines4/5

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

It explains matching semantics ('Terms match path SEGMENTS (all must appear)') and gives concrete narrowing guidance: 'Add method to narrow by verb, deprecated=true for the retiring ones.' It does not explicitly name sibling alternatives or exclusion cases, but the usage context is clear enough for an agent to decide when to call 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 tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0

Disambiguation3/5

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.

Naming Consistency3/5

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.

Tool Count2/5

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.

Completeness5/5

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.

Resources

Need Help?