run_vectorsReplay one evidence corpus with the bundled reference verifier to check conformance; returns per-vector results in paginated rows for inspection.
Replay one corpus with the bundled reference verifier; per-vector rows come back in pages.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| corpus | No | vectors | |
| offset | No |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, closed-world, non-destructive, so the safety profile is covered. The description adds two useful facts — the verifier is bundled/reference (local, deterministic) and results are paged per-vector rows — but says nothing about truncation, ordering, or failure handling.
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 compact sentence with the action front-loaded and no filler. It is efficient, though arguably too terse for a tool whose parameters are entirely undocumented.
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?
An output schema exists so return values needn't be explained, and annotations cover the safety profile. But with three undocumented parameters and 0% schema coverage, the agent still cannot tell what a valid corpus value looks like or how paging should be driven — a real gap for an otherwise simple 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 coverage is 0%, so the schema supplies no meaning for corpus, limit, or offset. The description only gestures at them ('one corpus', 'come back in pages') without explaining what corpus accepts (name vs. path), what the limit default of 50 means, or how offset behaves.
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?
States a specific verb and resource: 'Replay one corpus with the bundled reference verifier.' That's clear enough to distinguish from list_vector_corpora and explain_vector, though the description never names the alternatives to sharpen the contrast.
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 — you gather that this is the execution/conformance step of a vector workflow — but there is no explicit 'use this when you want to validate a corpus' or any exclusion against verify_* or explain_vector siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.