Triage Findings

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

Beyond the readOnlyHint and destructiveHint annotations, the description adds critical behavioral context: 'Triage never confirms anything' and explains how canary findings affect verdicts (weighted down). This exceeds what annotations alone convey.

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 front-loaded with the primary purpose and then adds relevant behavioral details. It is somewhat verbose with the canary explanation but remains focused and avoids unrelated information. Structure is clear, though minor redundancy exists.

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 and output expectations (e.g., 'the measurement is reported'), and the existing output schema (though not shown) likely provides structural details. It does not address edge cases or error handling, but for a triage tool, the description is sufficiently complete.

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 0%, and the description does not mention max_findings or min_severity at all. The description completely fails to compensate for the lack of parameter explanations, leaving the agent to guess their meaning.

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 tool's function: 'Run AI triage over candidate findings to cut false positives.' It also distinguishes itself from sibling tools by mentioning escalation to validate_findings, making its role specific and unambiguous.

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 provides implicit usage guidance by stating that escalated findings go to validate_findings, implying triage is a precursor to validation. It also notes the intentional inclusion of canary findings, which informs expected behavior. However, it does not explicitly list when to use vs. not use alternatives.

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