ai_classify

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

No annotations provided, so description must disclose behavior. Mentions 'configured free LLM' but lacks details on latency, cost, or determinism. Does not describe output format or error handling for invalid inputs. Adequate but not thorough.

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 only. First states core purpose, second adds key constraint. No filler, front-loaded with critical information.

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 simple two-parameter classification tool with no output schema, description covers purpose and input constraints. Missing details like output format (single label vs confidence scores) and label limits, but mostly complete given simplicity.

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 coverage is 100%, so baseline 3. Description adds 'plain prose' constraint for text and 'provided labels' for labels, but these are largely implicit in the schema. Does not add significant new meaning beyond the schema.

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?

Description clearly states classification of plain text into provided labels using an LLM. It specifies the verb 'classify' and resource 'plain text', and distinguishes from siblings like ai_generate or ai_summarize by focusing on categorization.

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?

Provides explicit constraint 'Plain prose only — no code, secrets, or file paths', guiding appropriate input. Does not explicitly mention when to use vs alternatives, but context suggests it's for categorization tasks distinct from other AI tools.

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