findings_storePersist QA findings by storing each claim with at least one evidence reference for later review. Records findings without grading, deduplicating, or resolving them.
Persist findings supplied by the caller. Each finding needs a claim and at least one evidence reference. This stores; it does not grade, dedupe, or resolve.
| Name | Required | Description | Default |
|---|---|---|---|
| run_id | Yes | ||
| verdict | No | the caller's verdict text, stored verbatim | |
| findings | Yes |
Changes observed during successful MCP inspections.
v0.4.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full behavioral burden. It usefully discloses that this is a write/persist operation and explicitly excludes grading, dedupe, and resolution, but omits idempotency, append-vs-replace behavior, permission requirements, and error 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?
Three tight sentences with the core action and boundary stated up front. Every sentence adds useful scope information without waste.
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 annotations, no output schema, and sparse parameter documentation, the description should do more. It does not explain return behavior, run_id semantics, duplicate handling, or what happens to verdict text.
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 only 33%. The description restates that each finding needs a claim and at least one evidence reference, which the schema already enforces, and says nothing about run_id, verdict, selector, or step.
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: persist findings. It also draws a clear boundary by saying it does not grade, dedupe, or resolve, though it does not explicitly name sibling alternatives.
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?
Implies the tool is used when the caller has findings to store and is not for grading, deduplication, or resolution. However, it does not state when to prefer this over sibling tools or mention prerequisites such as a valid run_id.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.