Validate AI-generated claims against source data to return VERIFIED, PARTIAL, or UNSUPPORTED labels per claim, helping users catch unsupported statements.
Validate AI-generated claims against actual source data. Implements Claim Ledger pattern. Returns VERIFIED / PARTIAL / UNSUPPORTED per claim.
| Name | Required | Description | Default |
|---|---|---|---|
| claims | Yes | List of claims to validate | |
| sources | Yes | Source data to validate against |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world, so the safety profile is fully covered. The description adds useful output semantics (per-claim VERIFIED / PARTIAL / UNSUPPORTED verdicts) but says nothing about what on its own makes a claim PARTIAL vs UNSUPPORTED, or about any matching/threshold behavior.
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 short, front-loaded sentences with no filler; the core action, the pattern, and the return taxonomy each earn their place.
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 correctly supplies the return values, and the two required inputs are conceptually clear from the name and schema. Slightly incomplete on how sources are consumed (url vs content) and any size limits, but adequate for a two-parameter read-only tool.
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% and both parameters are documented in the schema, so the baseline is 3. The description's phrase 'against actual source data' loosely reinforces the sources parameter but adds no format or constraint detail beyond the schema.
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 verb and resource ('Validate AI-generated claims against actual source data') and even states the domain pattern (Claim Ledger). It does not explicitly differentiate itself from siblings, but the sibling set (filter, proofer, generator tools) is far enough away that no real ambiguity exists.
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?
Usage is only implied: an agent can infer this is for checking claims against sources, but there is no statement of when to prefer it over alternatives, no preconditions, and no exclusions (e.g. claim count limits or source format requirements).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.