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

The description discloses that the tool performs 'pure local analysis: it collects nothing, stores nothing and reaches no network; the text never leaves the server.' This adds meaningful privacy and network behavior not covered by the annotations' readOnlyHint and idempotentHint. No contradiction exists.

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, front-loaded with the core action and output list, followed by a concise privacy note and usage directive. Every sentence serves a purpose, with no redundancy or filler.

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?

Given that there is no output schema, the description does a good job of listing the outputs (threat level, matched categories, financial-target flags, confidence score, recommended action) and the input scenario. It does not specify possible values or formats, but it provides sufficient context for understanding the tool's role and use case.

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 input schema already fully describes the single parameter ('text' with description 'the security text to classify — an advisory, alert or forum post'). The tool description repeats this phrasing almost verbatim without adding new meaning, so with 100% schema coverage, a baseline 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 identifies the resource ('a piece of security text') and the outputs (threat level, categories, flags, confidence, recommended action). This clearly distinguishes it from sibling tools like breach_news and check_exposure, which focus on retrieving data rather than analyzing text.

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 explicit context: 'Use it to triage findings surfaced by breach_news or from your own monitoring.' This tells the agent when to invoke the tool, though it does not name alternative tools or give when-not-to-use conditions.

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