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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior. The description adds useful behavioral context beyond these: newest-first ordering, the split-group scope, the recommendation to filter rather than paginate, and the existence of llmContext guidance in results. No contradiction with annotations.

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, no filler, and the most important behavioral facts are front-loaded: recency, ordering, and scope. The filter guidance and llmContext note each earn their place without redundancy.

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 rich input schema, full parameter coverage, a present output schema, and strong annotations, the description supplies the remaining practical context: ordering behavior, filter-first strategy, and follow-up instructions from results. Slight ambiguity in the phrase 'split group' prevents a 5, but nothing critical 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 schema itself documents all 10 parameters. The description adds a usage strategy by naming four filter parameters and saying to prefer filtering over pagination, but it does not add meaningfully richer semantics for individual parameters beyond what the schema already provides.

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 action and resource: 'List recent split runs, newest first'. It also distinguishes the tool's scope by noting '(split group)' and naming the distinct filter dimensions, which separates it from sibling run-listing tools like list_extract_runs or list_parse_runs.

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 explicit usage strategy: 'Filter rather than paginate' followed by the exact filter fields, and instructs the agent to follow any llmContext guidance in results. It does not explicitly state exclusions such as 'use get_split_run for a single run', but the guidance is clear and practical for invoking this tool correctly.

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