submit_findings

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

No annotations are provided, so the description carries the disclosure burden. It fully discloses that the tool is mutating and persists new records, and it adds useful context about the finding's meaning and lifecycle. It does not mention potential side effects like duplicates or permissions, but the core mutation semantics are clear.

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 well-structured: a clear opening sentence, a usage context, a conceptual comparison, and a lifecycle note. It is concise yet substantive, with no 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?

The description covers what the tool does, when to use it, how it relates to sibling tools, and what happens after submission. Since an output schema exists, return values do not need to be described. The only minor gap is server_version, but this is a small omission in an otherwise complete description.

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 schema already documents findings_json in detail, and the description adds semantic framing that helps the agent understand how to populate the parameters. However, server_version is undocumented in both the schema and description, and the description does not explain its purpose, preventing a perfect score.

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 opens with a specific verb and resource: 'Record negative findings ... against the model's controls.' It also explicitly states the mutating nature and distinguishes findings from assertions, making the tool's purpose unmistakable.

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 gives an explicit precondition: 'Use after a gap-discovery scan (see get_scan_prompt).' It also clearly contrasts with submit_assertions, explaining that findings are the negative counterpart and that the tool is for when expected control evidence was NOT found.

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