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

The description discloses key behavioral traits: it is a durable background job, returns a jobId, requires polling, and mentions credit reservation/settlement. This adds significant context beyond annotations, which only indicate non-readonly and non-idempotent. The credit behavior is particularly valuable and not inferable from 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?

The description is compact and informative, front-loading the purpose and key behavior. It includes the essential polling instruction and credit detail without redundancy. Minor redundancy with the tool's title but acceptable for a 3-sentence description.

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?

This is a complex tool with a nested input object and multiple parameters. Without an output schema, the description should clarify what the caller receives (jobId) and how to get results, which it does. It also mentions credit behavior and idempotency as context. Missing explicit instructions on when to use each heavy tool, but that is tool-specific; the job wrapper is described adequately.

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?

The schema covers toolName with examples and description, input as nested object, and idempotencyKey. Description adds the critical nuance that input is exactly what you would pass synchronously, which is not obvious from the schema alone. However, caseStudyId and researchRunId are undocumented in the description)Skip, but schema coverage at 60% is moderate, so the description partially compensates. Given the nested input object, the clarification is valuable, so 4 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 clearly states the tool starts a heavy research tool as a background job, explicitly lists the supported heavy tools, and distinguishes it from blocking calls. It also mentions the jobId and polling tool, making the purpose unambiguous and differentiated from siblings like ata_start_research_run or walk_forward_candidate.

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 explains when to use it (for heavy research tools) and references the alternative to a blocking call implicitly. It names the polling tool for follow-up. However, it does not explicitly state when not to use (e.g., for lightweight operations), but the context is clear enough for an agent.

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