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

With no annotations, the description carries the full burden of behavioral disclosure. It explicitly lists the return values (signed CausalCertificate, liability allocation, evidence-chain completeness, regulatory mapping, Bitcoin proof) and discloses the cost and guardrails. This is a solid amount of transparency, though it does not explain failure modes or exact evidence thresholds, which would push it to a 5.

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 three sentences long and front-loaded with the main purpose. Each sentence adds critical information: purpose, return values, cost, and guardrails. There is no fluff or repetition, making it concise and well-structured.

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 provides a comprehensive overview of what the tool does, what it returns, its cost, and its guardrails. For a complex submission tool with 11 parameters and no output schema, this is reasonably complete. However, it does not elaborate on the 'minimum evidence' requirement or error handling, leaving some gaps for an agent trying to use the tool confidently.

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 only 18% (2 out of 11 parameters have descriptions). The description mentions guardrails that map to `pii_acknowledged` and `deterministic_only`, but it does not explain the meaning or purpose of other parameters such as `agents`, `events`, `severity`, or `jurisdiction`. The description does not compensate for the low schema coverage, leaving many parameters underspecified.

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 starts with a specific verb and resource: 'Submit an AI incident for deterministic causal liability attribution.' This clearly identifies the tool's primary function and distinguishes it from siblings like submit_otel_trace (which submits telemetry) and evaluate_prospective_response (which evaluates responses). The purpose is unambiguous and the resource is well-defined.

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 clear context on when to use this tool: to submit an AI incident for liability attribution. It also mentions cost (50 credits) and three guardrails (PII scan, deterministic-only acknowledgement, minimum evidence), which help the agent understand prerequisites and constraints. However, it does not explicitly mention alternatives or exclusions, so it falls short of a 5.

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