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

Annotations already convey readOnlyHint=true, idempotentHint=true, and destructiveHint=false negative behavior. The description adds positive behavioral context beyond annotations: it reveals polling semantics, the list behavior when jobId is omitted, and the fact that the result is included once the job succeeds. 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?

The entire description is one front-loaded sentence that packs purpose, parameter behavior, and return payload into a compact form. Every phrase earns its place, with no filler or repetition of the title.

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?

For a read-only polling tool, the description covers the main action, the optional jobId behavior, and return fields (status, progress, credits, result). However, it does not clarify the undocumented caseStudyId and researchRunId parameters, nor define what 'recent jobs' means. With no output schema, a bit more detail on list-mode ordering or job lifecycle would make it complete, but it is still adequate.

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 50%: jobId and includeResult have descriptions, but caseStudyId and researchRunId do not. The tool description enriches jobId ('omit to list recent jobs') and hints at includeResult's effect ('full tool result once it succeeds'), but it adds no meaning for the two undocumented parameters, leaving the agent to guess their purpose.

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 uses a specific verb ('Poll') and a clear resource ('background research job') and names the exact data returned: status, progress, credits, and the full tool result. It also distinguishes the list mode ('omit jobId to list recent jobs') from the single-job polling mode, making its purpose unambiguous relative to sibling tools like workflow or task status.

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 clearly states when to use the tool: poll a background research job, or omit jobId to list recent jobs. It gives concrete invocation context, though it does not explicitly say when not to use it or name alternative sibling tools (e.g., ata_get_research_workflow_status).

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