From an OpenAPI, forge an MCP server design, per-operation tools, Agent Skills, an enriched OpenAPI, a server.json, and apis.json properties.
| Name | Required | Description | Default |
|---|---|---|---|
| document | Yes | The API description to operate on — OpenAPI, AsyncAPI, Arazzo or JSON Schema. A YAML/JSON string or an already-parsed object; both are accepted. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It describes what the tool produces (design, tools, skills, etc.) but does not mention side effects, whether it mutates input, authentication requirements, error behavior, or the format of the return value. The lack of specification regarding what 'forge' entails—whether it is a pure transformation, requires network access, or returns a single aggregate object—leaves significant ambiguity for an agent.
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 a single sentence that efficiently lists the key outputs, front-loading the source ('From an OpenAPI') before enumerating the generated artifacts. It is concise and avoids wordiness, though it packs many items into one clause, making it slightly dense but still readable.
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?
For a complex code-generation tool with no output schema, the description is insufficient. It does not explain the structure of the returned value, whether it is a JSON object with keys for each artifact, or how the artifacts are delivered (e.g., as strings, files, or nested objects). It also omits potential limitations or dependencies, making it hard for an agent to anticipate the tool's behavior and results. More context is needed for correct invocation and interpretation.
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?
The schema provides a comprehensive description of the 'document' parameter, covering accepted formats and input variants, so the baseline is 3. The tool description adds only a slight nuance by saying 'From an OpenAPI,' which is actually more restrictive than the schema's broader acceptance of AsyncAPI, Arazzo, and JSON Schema. This introduces a minor inconsistency and does not enhance parameter understanding; it remains at the baseline.
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 clearly states the tool's action (forge) and the resource (an MCP server design from an OpenAPI) along with a list of artifacts produced. It distinguishes itself from the sibling tools, which focus on analysis, search, and governance rather than code generation. However, it says 'OpenAPI' whereas the schema also accepts AsyncAPI, Arazzo, and JSON Schema, creating a slight mismatch between the stated scope and actual input types.
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 description provides no guidance on when to use this tool versus alternatives. It does not mention any conditions, prerequisites, or contrast with other tools, leaving the agent to infer that it is for generating MCP server artifacts. This is a notable gap given the large sibling set with overlapping API-related operations.
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.
Most tools have distinct purposes with clear descriptions, reducing ambiguity. However, some overlap exists between search tools like 'find_posts' and 'search_api_evangelist', though they target different scopes (stories vs. unified search). Overall, an agent can reasonably differentiate them.
The majority of tools follow a verb_noun pattern (e.g., find_areas, get_post), but several use noun_noun or inconsistent prefixes (e.g., api_coverage, company_gaps, insights_adoption). This inconsistency can confuse pattern recognition, though the pattern is still readable.
With 56 tools, the server is overloaded for a typical MCP context. While the domain is broad, the sheer number risks agent confusion and selection errors. Calibration suggests 25+ tools are excessive, and this server far exceeds that threshold.
The tool set covers a wide range of API governance, search, analysis, and generation tasks. There are no obvious dead ends for navigating the API Evangelist network, though some areas (e.g., direct API creation) are intentionally out of scope. Minor consolidation could improve efficiency.
