API discovery and selection for AI agents connecting to the physical world.
Scored across 1 tool
There is only one tool, so there is no possibility of misselection or overlapping purposes. Its role is clear as the server's sole operation.
The single tool name find_api_for_task follows a clear snake_case verb_noun pattern. With only one tool, consistency is trivially maintained.
A single tool may be appropriate for a focused ranking endpoint, but it feels thin for a server named RealWorldAPIs that implies a broader catalog. It sits at the borderline of being too limited rather than being clearly well-scoped.
The tool covers task-based API ranking, but the surface lacks list, browse, or get-details operations that an agent might need for catalog exploration. This creates notable gaps for non-ranking lookups.
Rank the audited RealWorldAPIs catalog for a natural-language real-world API task. Put every structured must-have constraint inside the requirements object. The server also accepts flattened top-level requirement aliases for compatibility, but requirements is the canonical shape. When presenting results, use only returned RWAPIS facts; do not infer comparative reliability, performance, quality, coverage, ease of use, enterprise suitability, or free-tier generosity.
| Name | Required | Description | Default |
|---|---|---|---|
| task | Yes | Natural-language description of what the agent or application needs to do. State hard requirements explicitly, for example: 'must support MCP'. | |
| limit | No | Maximum number of ranked recommendations to return. | |
| requirements | No | Canonical location for structured hard constraints. Do not put capabilities, mcp, openapi, auth, free_tier, category, or min_readiness at the top level. |
| Name | Required | Description |
|---|---|---|
| name | Yes | |
| task | Yes | |
| caveat | Yes | |
| catalog_size | Yes | |
| agent_summary | Yes | |
| eligible_count | Yes | |
| engine_version | Yes | |
| recommendations | Yes | |
| input_normalization | No | |
| requirements_applied | No | |
| requirements_detected | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish that this is read-only, idempotent, non-destructive, and closed-world. The description adds behavioral context beyond that: the server accepts flattened aliases for compatibility, requirements is the canonical input shape, and results must be interpreted only from returned RWAPIS facts without inferring comparative reliability or quality. It does not, however, describe the ranking logic itself.
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?
The description is four compact sentences, front-loaded with the purpose and followed by input-shaping guidance and output interpretation cautions. Every sentence contributes useful information without repetition or filler.
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?
Given the rich input schema, output schema, and annotations, the description covers what the tool does, how to structure hard constraints, compatibility behavior, and result presentation limits. Nothing essential for correct invocation appears 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?
Schema coverage is 100%, so the schema already documents the task, limit, and nested requirements fields. The description adds useful semantics beyond the schema by specifying the canonical requirements object and noting compatibility with flattened top-level aliases. This helps an agent choose the correct input shape.
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 states a specific verb ('Rank'), a specific resource ('audited RealWorldAPIs catalog'), and the input context ('natural-language real-world API task'). No sibling tools exist, so no sibling differentiation is needed. The purpose is immediately clear.
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?
It clearly says to use this tool for natural-language real-world API tasks and instructs that structured hard constraints belong in the requirements object. It also explains canonical versus compatibility alias input shapes. It does not explicitly state when not to use it, but there are no alternatives or siblings to route against.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
find_api_for_taskAI service marketplace — agents discover, call, and pay for API services automatically.
Turn any task into the right API calls: discover, evaluate, and integrate public APIs.
Demand-side discovery for the agent economy: turn ambiguous intentions into commitments and match th
Stripe-native marketplace where AI agents discover and pay per call for API services.
