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

Annotations already mark the tool as read-only and non-destructive, and the description adds genuinely useful behavioral detail: confidence is calibrated with concrete thresholds, answers below 0.5 are characterized, and the 'smart' tier re-asks uncertain items via a reasoning model. This goes well beyond what annotations alone convey.

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 three purposeful sentences: core behavior, use cases, and confidence/tier behavior. Nothing is redundant, and the most important constraint ('exactly one label', 1,000 max) is front-loaded.

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 classification tool with an output schema and read-only/idempotent annotations, the description covers limits, calibration, tier behavior, and actionable guidance for low-confidence results. An agent has everything needed to invoke it correctly and interpret the consequences.

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 the burden on the description is lower, but it still adds meaning beyond the schema by explaining what 'calibrated confidence' means and how the 'smart' tier behaves relative to confidence thresholds. This helps the agent reason about parameter choices without opening 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?

The description opens with a specific verb and resource: 'Sort up to 1,000 texts into exactly one of your own labels each, with a calibrated confidence per answer.' This clearly distinguishes it from the sibling classify_multi_label by emphasizing single-label output, and the 1,000-item constraint adds precision.

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?

It gives explicit when-to-use context ('many items to triage, route, filter or bucket and do not want to read them all') with concrete examples, and an explicit when-not-to-use rule ('Do not use it for fewer than about five items you can already see — just decide'). This is strong practical guidance for an agent choosing between tools.

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