Vouch

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.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full behavioral disclosure burden. It goes beyond a generic 'compare' by explaining that each tool keeps its own score and tier, that results are not collapsed, and that a caveat is surfaced for mismatched tiers. This is meaningful behavioral detail, though it does not describe the exact output format.

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, all informative and appropriately front-loaded: what the tool does, when to use it, and an important behavioral caveat. There is no redundant filler or repetition of schema details.

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 tool with no output schema and no annotations, the description covers purpose, usage, and key behavioral output semantics (per-tool score/tier, caveat on tier mismatch). It is nearly complete, though it leaves the exact response representation unspecified.

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% and the only parameter is already well documented in the schema ('Tool names, packages, or servers — free text, one per tool'). The description reinforces the context but does not add new parameter-level meaning beyond what the input schema provides, so the baseline of 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?

The description states a specific action ('compare'), a specific resource ('MCP tools'), and a clear scope ('2-5', 'side by side'). It also conveys what the tool intentionally does not do—collapse results into a single ranked number—which sharply differentiates it from the check/find siblings.

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 explicitly says when to call the tool: 'Call this when weighing alternatives for the same task.' This gives clear selection context, though it does not explicitly name sibling alternatives or state when not to use it, so it falls just short of full exclusions guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the transparency burden. It discloses that this is a search operation, that results are ranked by measured reliability, and it defines what the 'deep' and 'shallow' tier filters mean. It does not mention output format, pagination, or side effects, but the essential behavior is clearly conveyed.

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, well-structured sentence that front-loads the core purpose, then provides use-case context and optional filtering details. There is no repetition of schema information and no filler. Every clause adds value.

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 search tool with three flat parameters and no output schema, the description covers the search intent, ranking behavior, and tier filtering. It does not describe the exact output shape, but the phrase 'options ranked by measured reliability' gives a reasonable expectation. A sibling-tool mention would make it more complete.

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 input schema covers 67% of parameters with descriptions, and the tool description adds meaningful context: it explains the query purpose and defines the tier values. The 'limit' parameter lacks description, though its min/max constraints are visible in the schema. The added tier definitions go beyond the schema, justifying a 4.

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 uses a specific verb ('Search') and a specific resource ('Vouch's independently measured corpus of MCP tools'), clearly distinguishing this from the sibling tools vouch_check and vouch_compare. The emphasis on 'measured reliability rather than popularity' further differentiates it from generic search tools.

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 explicitly states when to call this tool: 'when choosing an MCP tool for a task and you want options ranked by measured reliability'. It gives clear usage context but does not name sibling alternatives or state when not to use it, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.