classify

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that the tool runs 'choice' once per item, automatically appends the item to the question, aggregates results, and returns a detailed JSON structure including confidence, probabilities, summary counts, latency, and usage. It does not discuss error behavior or potential costs, but it gives a strong operational picture.

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 well-structured with a concise summary sentence, use cases, an Args section, and a Returns section. Every part earns its place: the summary explains what the tool does, Args documents each parameter, and Returns tells the agent exactly what to expect. There is no redundant 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?

The tool is moderately complex with four parameters and a structured return value. The description covers parameters, constraints, execution behavior, and the complete return shape. It could be slightly more complete by explaining what 'Jev' is or clarifying error modes, but nothing essential is missing for an agent to invoke the tool correctly.

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 description coverage is 0%, so the description must compensate fully. It does: items are '1-100 non-empty strings,' options are a 'Mapping of short unique id -> one-line category description' with '2-100 options,' question has a default and is auto-appended with the item, and context is optional. This adds meaningful constraints and semantics beyond the plain JSON 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?

The description immediately states the core action: 'Batch-classify up to 100 items against ONE shared set of categories using Jev.' It also explains that it wraps the 'choice' question type and aggregates results, which differentiates it from the single-item sibling tool 'choice'. Concrete examples like routing support tickets and labeling log lines further clarify the intended resource and function.

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 clear context for when to use the tool, such as 'routing support tickets, labeling log lines, triaging inbox items' and says it is 'Much cheaper and faster than an LLM for mechanical labeling.' It does not explicitly state when not to use it or contrast it directly with sibling alternatives, but the batch-vs-single distinction is implied through the 'choice question type once per item' phrasing.

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