Turn a governance ruleset into agent-native guidance — an AGENTS.md block, a system-prompt set, a per-rule remediation pack, and a digest — so agents follow the rules while authoring, not after linting.
| Name | Required | Description | Default |
|---|---|---|---|
| ruleset | Yes | A Spectral ruleset to run instead of the catalog default. Score against rules you never adopted means little — pass your own. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With zero annotations, the description carries full behavioral burden. It discloses what gets produced (four artifact types), which is valuable. However, it never clarifies the operational semantics of 'export' — whether it writes files, returns a payload, or mutates state. Side effects, authentication needs, and failure behavior (e.g., invalid ruleset handling) are all unspecified.
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 dense sentence with zero filler. The verb and resource are front-loaded, the output list is concrete, and the purpose clause earns its place by differentiating the tool from lint-time approaches. Slightly dense due to the four-item em-dash list, but every clause contributes.
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 and no annotations, the description must cover returns and side effects itself. It enumerates the output artifacts, which mitigates the missing output schema, but leaves operational details open: input format expectations for the Spectral ruleset, persistence behavior, and return structure. In a 50+ sibling toolset with several governance tools, sharper operational clarity would be needed for full completeness.
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 the schema already documents the sole parameter well: it's a Spectral ruleset overriding the catalog default, with rationale ('Score against rules you never adopted means little'). The tool description doesn't add parameter-level detail beyond that, which is acceptable at the baseline 3 since the schema does the heavy lifting.
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 ('Turn') and resource ('governance ruleset') and enumerates four concrete output artifacts (AGENTS.md block, system-prompt set, per-rule remediation pack, digest). The purpose clause ('so agents follow the rules while authoring, not after linting') clearly distinguishes it from governance_report, govern_estate, and validate_api siblings since it produces actionable authoring-time guidance rather than metrics or validation results.
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 implies when to use the tool via 'while authoring, not after linting,' suggesting it complements linting-style tools like validate_api. However, it never explicitly names alternatives, states when NOT to use it, or gives conditions for choosing between this and governance_report or govern_estate. Usage guidance is implied but left to inference.
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.
