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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering the safety profile. The description adds value beyond that by explaining the 'durable' nature of the job and setting expectations that a complete result includes a query-ready dataset ID and sample/paid query URLs. 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. The verb and resource are front-loaded, and the second sentence efficiently clarifies what a successful poll looks like. Every word earns its place.

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 simple one-parameter polling tool with rich annotations, the description is largely sufficient. The main gaps are the lack of explicit mention of in-progress statuses/error handling and the absence of guidance on polling intervals, but the tool's low complexity reduces the severity of these omissions.

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 0%, so the description must carry the burden for parameter meaning. It implies that materialization_id identifies the job to poll, but it never explicitly names or defines it. It also doesn't describe possible intermediate statuses (e.g., pending, in-progress, failed), leaving some ambiguity about what the parameter's polling target returns.

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 ('Poll') and a specific resource ('a durable materialization job'), making the tool's purpose unmistakable. It also distinguishes it from siblings like aggregate_imported_dataset, get_coverage_status, and search_discovered_data, which concern different operations or resources.

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 provides clear context: this tool is for polling the status of a durable materialization job, which implies a long-running async process. It does not, however, explicitly state exclusions or name alternative tools for querying the resulting data directly, so it falls short of a 5.

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