firewall_outcome

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the learning effect (402Sentinel learns and downweights noisy signals), notes that hard-block safety signals stay deterministic, and includes the cost signal 'FREE'. This goes beyond a simple 'report outcome' and gives the agent useful behavioral context, though it does not cover error cases or response behavior.

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 compact and front-loaded with the action and cost signal ('FREE'). The learning explanation is concise yet informative, and the final sentence about the assessment_id is directly actionable. Every sentence earns its place with no wasted words.

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?

For a simple two-parameter tool with full schema coverage and no output schema, the description provides the essential workflow (post-firewall feedback) and the provenance requirement for assessment_id. It is missing an explicit comparison to the sibling 'report_outcome', which could cause an agent to pick the wrong tool, but overall the core context is sufficiently covered.

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 100%, and the schema already documents both parameters, including the fw_… prefix for assessment_id and the grouping of outcome values into bad/good. The description adds no significant parameter-level detail beyond the schema; the reminder to pass the assessment_id is redundant with the schema's own description.

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 states a specific action: reporting what actually happened after a firewall verdict, with a clear resource (the assessment_id from a prior firewall call). It effectively communicates the tool's role as a feedback mechanism. However, it does not explicitly differentiate itself from the sibling tool 'report_outcome', leaving some ambiguity about which outcome-reporting tool to choose.

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 clearly indicates this tool is used after a firewall verdict and instructs the agent to pass the assessment_id from a prior firewall call, giving a direct usage context. It does not explicitly mention when not to use it or name alternatives, but the condition 'after a firewall verdict' is a clear usage guideline.

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