An API's primary OpenAPI reference (url) — the top agent intent; set include=["content"] to inline the spec body.
| Name | Required | Description | Default |
|---|---|---|---|
| aid | Yes | API id in the form provider:api-slug, as find_apis returns it, e.g. "stripe:stripe-api". | |
| context | No | Optional: one sentence on why you are asking. Never used to rank; read only if a result is wrong. | |
| include | No | Pass ["content"] to inline each artifact's body instead of just its URL. |
Changes observed during successful MCP inspections.
Input schema / properties / context / descriptionPrevious 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."Input schema / properties / aid / descriptionAdded value: +"API id in the form provider:api-slug, as find_apis returns it, e.g. \"stripe:stripe-api\"."Input schema / properties / include / descriptionAdded value: +"Pass [\"content\"] to inline each artifact's body instead of just its URL."Input schema / properties / contextAdded 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"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful behavioral detail beyond that: the default return is only the URL, and passing include=["content"] changes the payload to inline the spec body, which tells the agent how to control response size.
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?
A single front-loaded sentence that leads with what is returned and then the opt-in for the full body. It is dense but every clause carries information; only 'the top agent intent' is 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?
With no output schema, the description does the work of explaining the two possible return shapes (URL vs inlined content), which is the key thing an agent needs. It stops short of covering failure modes (e.g., an API with no OpenAPI reference), leaving a minor 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 description coverage is 100%, so all three parameters (aid, context, include) are already documented in the schema, including the enum value 'content'. The description reinforces the include behavior but adds no syntax or format detail beyond the schema; baseline 3 applies.
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?
States the specific resource (an API's primary OpenAPI reference) and its default output (url), which distinguishes it from search-oriented siblings like find_openapis. The phrase 'the top agent intent' is more positioning than purpose, and the verb 'get' is implicit rather than stated.
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 top agent intent' weakly implies this is the preferred first retrieval call, but no explicit when/when-not guidance or named alternatives (find_openapis, get_api_artifacts, get_provider_schema) are given. Usage must be inferred from the surrounding tool family.
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.