vouch_checkGet an MCP tool's independently measured trust score before relying on it: real invocation trials, not self-reported metadata. Call this before adding a new MCP server to a project, or when deciding between two tools that do similar things. Look up by tool name, package, or server — free text.
| Name | Required | Description | Default |
|---|---|---|---|
| tool | Yes | A tool name, 'server tool', or package name — free text. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden of behavioral disclosure. It meaningfully explains that the score is based on 'real invocation trials, not self-reported metadata,' and frames the operation as a read-style lookup ('Get,' 'Look up'). It does not describe output format or score scale, but the provenance and non-self-reported nature of the result are well articulated.
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?
Three sentences, each earning its place: the first states the core value and measurement basis, the second gives usage timing, and the third specifies input format. The most important information is front-loaded and there is no redundant 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?
For a simple one-parameter lookup with no output schema, the description covers what the tool does, how the score is obtained, when to call it, and how to provide input. It could mention the returned score's format or range, but the core information an agent needs to invoke it correctly is present.
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 single parameter is already fully described in the schema ('A tool name, 'server tool', or package name — free text'), and the description adds little beyond repeating the same lookup scope. With 100% schema coverage, the baseline of 3 is appropriate.
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 names a specific action and resource: 'Get an MCP tool's independently measured trust score.' It also grounds the tool's purpose with concrete details ('real invocation trials, not self-reported metadata') and lookup scope ('tool name, package, or server'), which makes it distinct from the sibling tools vouch_compare and vouch_find.
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 gives clear trigger conditions: call this before adding a new MCP server or when deciding between similar tools. It does not explicitly mention when not to use it or directly contrast it with vouch_compare/vouch_find, but the stated use cases are specific enough for an agent to select this tool in the right situations.
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.
Each tool has a distinct role: vouch_check looks up a single tool's score, vouch_compare compares multiple tools side-by-side, and vouch_find searches the corpus. There is slight overlap between vouch_check and vouch_find since both accept free-text queries, but their intended use cases are clearly differentiated.
All tool names follow a consistent vouch_ + verb pattern: vouch_check, vouch_compare, vouch_find. This makes the set predictable and easy to navigate.
Three tools is well-scoped for this server's purpose: search for options, check one, compare alternatives. Each tool has a clear, non-redundant role and the count feels appropriate without being thin or bloated.
The tool surface covers the full workflow an agent needs when evaluating MCP tools: finding candidates, checking a specific tool's trust score, and comparing multiple tools. No obvious gaps exist for the stated domain.