triage_findings

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

With no annotations provided, description carries full burden. It discloses deterministic behavior, no model calls, no API key needed, and that output is a reasoning bundle. This adequately informs the agent of side-effect-free, localized processing. A minor gap: no mention of error handling or format, but sufficient for core traits.

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 sentences, each essential. First sentence defines purpose, second adds behavioral traits, third gives usage flow. Front-loaded with core purpose. No verbosity or redundancy.

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?

Given a single parameter with high schema coverage, no output schema, and sibling tools including apply_triage, the description is complete. It explains what the tool produces, how it fits in the workflow, and key constraints. No missing information for an agent to use it correctly.

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 has 100% coverage with description for 'findings'. Description adds valuable context: specify 'array from scan_path --format json', clarifying source and format. This goes beyond schema by providing concrete usage instructions, aiding correct invocation.

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?

Description clearly states the tool produces a triage request bundle, specifying the action ('produce') and resource ('triage request bundle'). It distinguishes from sibling tools like apply_triage and remediate_findings by clarifying this tool only prepares data for reasoning, not execution.

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?

Explicitly tells the agent to assess findings then call apply_triage with verdicts, establishing a clear workflow. Also notes the tool needs no API key and doesn't call a model, guiding appropriate usage. Could strengthen with explicit 'do not use for X' but current guidance is strong.

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