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

The description discloses important behavioral traits beyond any annotations: it is 'Claude-powered' (LLM-based), a 'pre-processing convenience tool' with a deterministic scoring engine that remains LLM-free, and it costs 10 credits. This gives the agent awareness of non-determinism, cost, and its auxiliary role. It does not mention potential failure modes or rate limits, but the provided context is substantial given no annotations exist.

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 composed of three sentences plus a note. It leads with the tool's core function, then describes the output and adds important caveats. Each sentence earns its place, though the length is slightly above minimal. No fluff is present, and key details (cost, LLM nature) are efficiently included.

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?

Despite having no output schema and no annotations, the description covers the essential context: what the tool does, what it returns, its relationship to submit_incident, cost, and its LLM-based nature. It is complete enough for an agent to use it correctly without needing additional documentation. A perfect score is withheld because it does not mention error handling or clarify the 'agents, events' fields in more detail.

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?

The schema already provides 100% coverage for all three parameters, so the description does not need to explain them. The description adds contextual value by detailing the output (agents, events, severity, jurisdiction, financial impact) which indirectly relates to the text and hint parameters, but it does not elaborate on parameter syntax or formats beyond the schema. This aligns with the baseline 3 for 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 identifies the tool as an extractor that parses unstructured text into a typed JSON schema, explicitly naming the resource (unstructured text) and the output format required by submit_incident. It distinguishes itself from sibling tools by positioning itself as a pre-processing convenience for incident submission, not as a submission, evaluation, or simulation tool.

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 states that the tool parses text into the schema required by submit_incident, which strongly implies it should be used before submission to prepare incident data. It provides clear context for when to use it, though it does not explicitly mention alternatives or when not to use it. The note about being a pre-processing tool adds further clarity.

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