RealWorldAPIs

Search Verified Capabilities

search_capabilities

Read-onlyIdempotent

Search the canonical 770-capability Verified/High decision graph directly. Use this when the question is about what an agent can actually do and under what execution conditions: task/capability text, API, category, action type, acted-on object, human approval, physical consequence, irreversibility, sandbox, hardware dependency, access friction or setup. All supplied filter groups combine with AND logic; multiple values inside one array filter are alternatives (OR). Unknown remains Unknown and may be filtered explicitly by passing the literal value Unknown.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum capability rows returned. total_matches reports the full match count.
`query`	No	Optional case-insensitive text search across API/provider/category, capability key/name, primitive/action type, object, execution fields and constraints. Search terms may match across different capability fields; all supplied terms must be present somewhere in the capability record.
`object`	No	Case-insensitive substring match on the object acted upon, such as smart lock, parcel or charging session.
`sandbox`	No	Exact sandbox/test-environment labels, including Unknown when desired.
`api_slugs`	No	Optional API slugs. Multiple values are OR within this filter.
`categories`	No	Exact category labels. Multiple values are OR within this filter.
`primitives`	No	Exact capability primitives such as Observe, Locate, Predict, Plan, Control or Act.
`agent_setup`	No	Exact agent-setup labels such as Fully self-service or Human setup required.
`action_types`	No	Exact action types such as Read, Search, Analyze, Route or Control.
`actionability`	No	Exact actionability labels such as Information only, Planning or Physical action.
`human_approval`	No	Exact approval labels, for example Required, Not required, Depends on action or Unknown.
`access_friction`	No	Exact access-friction labels such as Self-service signup, Sales contract or Hardware ecosystem.
`hardware_dependency`	No	Exact hardware-dependency labels.
`physical_consequence`	No	When supplied, require the exact physical-consequence boolean.
`irreversible_high_consequence`	No	When supplied, require the exact irreversible/high-consequence boolean.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`name`	Yes
`method`	Yes
`source`	Yes
`filters`	Yes
`results`	Yes
`returned`	Yes
`total_matches`	Yes
`evidence_policy`	Yes
`machine_schema_version`	No
`capability_snapshot_date`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 30, 2026

changedInput schema / properties / query / description

Previous value: -"Optional case-insensitive text search across API/provider/category, capability key/name, primitive/action type, object, execution fields and constraints."New value: +"Optional case-insensitive text search across API/provider/category, capability key/name, primitive/action type, object, execution fields and constraints. Search terms may match across different capability fields; all supplied terms must be present somewhere in the capability record."

AddedSep 30, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare read-only, non-destructive, idempotent and closed-world behavior. The description adds meaningful query behavior beyond annotations: cross-filter AND logic, OR-within-array semantics, and explicit Unknown filtering.

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

Conciseness5/5

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

Three sentences, front-loaded with the core action and resource. The long use-case list is dense but earns its place by routing the agent, and the filter-logic sentence is essential.

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 15 optional parameters, a full input schema, an output schema, and safety annotations, the description supplies the missing query-composition and Unknown-handling rules. Nothing critical for correct invocation is absent.

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

Parameters4/5

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

Schema covers all 15 parameters at 100%, so the baseline is 3. The description adds cross-parameter semantics not fully stated in the schema, especially that filter groups combine with AND and array values combine with OR.

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 and resource: search the canonical 770-capability Verified/High decision graph. The scope and domain are clear enough to distinguish it from sibling API-search tools like search_apis and find_api_for_task.

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?

Explicitly says when to use this tool: questions about what an agent can actually do and under what execution conditions, listing relevant filter dimensions. It does not name alternative siblings or when not to use it, so it falls short of a 5.

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

All RealWorldAPIs tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.