assess_threat

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

The description adds meaningful behavioral context beyond the annotations: 'Pure local analysis: it collects nothing, stores nothing and reaches no network; the text never leaves the server.' This privacy/network guarantee is not visible in the annotations and is valuable for an AI agent handling sensitive data. It also lists the output fields, complementing the readOnly and idempotent hints.

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 two sentences and 69 words, with the core action and outputs stated first, followed by privacy guarantees and usage guidance. Every clause adds value without repetition or fluff, making it highly 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?

Despite lacking an output schema, the description enumerates all key return elements (threat level, categories, flags, confidence, action) and clearly defines the single input parameter. The tool is simple (one required parameter, no enums/nested objects), and the description covers its purpose, behavior, and usage context fully. It is complete for an agent to decide when and how to call it.

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 parameter 'text' is fully described in the input schema (100% coverage) with the same phrasing used in the tool description ('security text to classify — an advisory, alert or forum post'). The description adds no new semantic detail beyond what the schema already provides, so the baseline of 3 is appropriate.

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 uses a specific verb ('Classify') and names both the input ('security text you supply — an advisory, alert or forum post') and the outputs ('threat level, matched categories, financial-target flags, a confidence score and a recommended action'). It also distinguishes itself from siblings by framing the tool as a triage step for findings from 'breach_news' or personal monitoring, which clearly differentiates it from feed or exposure tools.

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 gives a clear use case: 'Use it to triage findings surfaced by breach_news or from your own monitoring.' This provides context for when to invoke the tool relative to siblings, though it does not explicitly state when not to use it or name alternative tools. The contrast with sibling tools (news fetching, exposure checking) is implicit but sufficient.

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