intelligence_classify_messages

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, so the description is not burdened with the safety profile. It adds valuable behavioral context beyond annotations: the classification is performed 'using the client's LLM' (implying cost/latency), it covers 'recent messages,' and the return value includes 'sampling_used,' which hints at possible sampling behavior rather than full classification.

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 concise and well-structured with clear 'Purpose,' 'When to use,' and 'Returns' sections. Each section earns its place, and the most important information is front-loaded in the first sentence.

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?

With a full output schema provided, the description does not need to explain return structure in detail, but it still summarizes the return object and adds sampling_used. Combined with annotations and clear usage guidance, the description is complete for an agent to select and 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 100%, so parameters (channel_id, categories, limit) are already well-documented in the schema. The description does not add parameter-specific semantics beyond the general suggestion of 'provided categories' and 'recent messages,' which is acceptable given the high schema coverage; 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 opens with a specific verb ('Classify') and resource ('recent messages') plus category labels, clearly distinguishing it from sibling tools like intelligence_summarize_channel and intelligence_extract_entities. It also adds the unique detail that each classification carries a 0-1 confidence score.

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 'When to use' section explicitly lists concrete use cases: triage spam vs. question vs. discussion, bucket support requests, and segment conversations. It does not explicitly name alternatives or state when not to use, but the provided context is clear enough for an agent to select the tool appropriately.

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