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

Annotations already cover read-only, idempotent, and non-destructive behavior. The description adds valuable nuance by clarifying that confidence is deterministic routing confidence (not statistical) and that UNCLASSIFIED is returned when no reliable route is detected, which goes beyond the annotation 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?

Two sentences, zero wasted words. The primary action and categories are front-loaded, and the confidence nuance is placed at the end for clarity. Perfectly sized for the information conveyed.

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 single-parameter classification tool with annotations covering safety, the description is nearly complete. It enumerates output categories and explains confidence semantics, but it does not explicitly define the return structure (e.g., does it return just a string or an object with type and confidence?). Given no output schema, this small gap leaves some ambiguity.

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 description for the 'description' parameter is complete (100% coverage) and includes examples. The tool description only reuses 'task description' without adding new semantic meaning, so it meets the baseline but adds no extra value.

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 verb ('Classify') and a precise resource ('task description'), enumerates all nine task types plus the UNCLASSIFIED fallback. It clearly distinguishes this tool from the sibling 'get_*' tools by its classification purpose.

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 implies usage for classifying task descriptions, and the sibling names are all 'get_*' retrieval tools, making the differentiator obvious. However, it does not explicitly state when not to use this tool or how it relates to the alternatives, leaving no exclusion guidance.

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