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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds useful behavioral context beyond those: results are ordered newest first, filtering is preferred over pagination, and any llmContext guidance in results should be followed. This is meaningful operational guidance that the annotations do not provide.

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 with no filler: the core action and ordering are front-loaded, then filters are summarized, then the llmContext instruction is given. Every sentence earns its place and the description is compact yet informative.

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 an output schema present and annotations covering read-only/idempotent safety, the description covers the remaining important context: ordering, filtering strategy, and how to handle llmContext guidance in results. Nothing essential for correct invocation is missing.

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 the parameters are already fully documented. The description merely lists some filter parameters that are already present in the schema, adding no new type, format, or semantic detail. The filter-rather-than-paginate advice is usage guidance rather than parameter-level semantics.

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 and resource: 'List recent classify runs, newest first.' The phrase '(classify group)' further distinguishes it from sibling list tools like list_extract_runs, list_parse_runs, and list_split_runs. It is immediately clear what the tool does and how it differs from others.

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 gives practical guidance: 'Filter rather than paginate' and enumerates the relevant filter fields (status, classifierId, batchId, fileNameContains). This tells the agent a strategy for narrowing results. It does not explicitly name alternatives like get_classify_run for fetching a single run, so it misses the full when-to-use-versus-alternatives picture.

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