Learn False Positive

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

Annotations declare destructiveHint=true, and the description adds valuable context beyond that: it specifies the storage location (.argus/learned.json), the persistent suppression effect on future runs, and the benefit (precision improves with use). This goes beyond the bare destructive flag, though it does not address reversibility or duplicate handling. No contradiction with annotations.

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?

Two concise sentences that lead with the primary purpose, then provide the behavioral outcome. No fluff, every clause adds value. The structure is ideal for an agent scanning the definition.

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 the core behavior required to invoke the tool correctly: what it does, where it stores data, and the long-term effect. Missing details like idempotency or what happens on repeated submissions are not critical for basic usage, and the absence of an output schema is acceptable for a mutation tool. Overall, it is complete enough for a typical call.

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 covers 75% of parameters with descriptions (path, reason, category), but the 'file' parameter lacks a description in both schema and tool description. The description does not elaborate on parameter relationships or format, so it adds little beyond the schema. Baseline 3 applies given high schema coverage.

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 clearly states the specific action (teach ARGUS that a finding is a false positive) and the resource (ARGUS). It also explains the persistent effect (remembered in .argus/learned.json and suppressed on future runs), which distinguishes it from sibling tools that analyze or report findings. Unlike ambiguous verbs like 'process', it is precise and actionable.

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 implies the use case: when you want to teach ARGUS a false positive pattern. It does not explicitly compare against siblings like ground_finding or learned_patterns, but the purpose is clear enough for an agent to infer when to invoke it. It lacks an explicit 'when not to use', but the context is straightforward.

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