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

Annotations already declare read-only/idempotent safe behavior, and the description adds concrete operational detail: default ordering, filter-before-pagination advice, the batchId fallback for batch tracking, the meaning of NEEDS_REVIEW (paused for human review), and the directive to follow llmContext guidance in results. These traits go well beyond what annotations or schema 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?

Five short sentences, all information-dense and front-loaded with the core purpose. The batchId workaround and llmContext note earn their place as tool-specific behavior an agent must know. The phrase 'workflows group' is slightly vague but doesn't add bloat.

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?

Given read-only annotations, 100% parameter description coverage, and an output schema, the description covers the remaining operational essentials: ordering, filtering strategy, batch tracking, status special case, and result-processing instructions. An agent can select and invoke this tool correctly without further investigation.

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 covers all 10 parameters, so baseline is 3; the description adds meaning by calling out the key filters (status, workflowId, batchId, fileNameContains) and explaining that batchId is the way to track workflow batches. It also clarifies the NEEDS_REVIEW enum value, which the schema lists without explanation.

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?

States a specific verb ('List') and resource ('workflow runs'), with ordering behavior ('newest first'). The '(workflows group)' qualifier and the named filter fields differentiate it from sibling list_* tools for extract/classify/parse/split runs. No ambiguity about what is returned.

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?

Explicitly instructs to filter rather than paginate, naming the exact filter parameters. Notes that workflow batches have no batch-get endpoint, so batchId tracking should happen through this tool. It gives clear context and a specific alternative, though it doesn't explicitly compare against other list_* sibling tools by name.

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