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

Annotations already declare readOnlyHint=true, so the description doesn't need to restate that. It adds substantial behavioral context: the tool is token-light (returns a small fixed shape, no step payloads), and it explains the meaning of the retryable field and the stalled-run heuristic. The only minor gap is not describing pagination or rate limits, but for a single-project poller this is sufficient. The description adds value beyond the annotation without contradicting it.

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 dense but well-structured: it front-loads the core purpose and return fields, then explains the failure diagnostics and the stalled-run heuristic, and ends with a token-light note. Every sentence adds value, and the structure guides the agent from what it returns to how to interpret it. No fluff or repetition.

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 poller with a single parameter and no output schema, the description is complete. It covers the return shape, the failure diagnostics semantics, the retryable field's three states, and the stalled-run edge case. The agent has everything it needs to call the tool and interpret the result correctly. The readOnlyHint annotation covers the safety profile, and the description covers the behavioral nuances.

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 compensate. It does not explicitly describe the projectId parameter, but the parameter is a simple UUID with a clear name and the description's context ('for a project') makes its purpose obvious. The description focuses on the return shape, which is the more complex part. Given the single simple parameter, the description provides adequate context, though it could have explicitly stated that projectId identifies the project whose latest run is polled.

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 polls the latest research run for a project and lists the exact fields returned (runId, status, phase, progress, elapsed, failure diagnostics). It distinguishes itself from siblings like get_draft_status and get_account_status by focusing on research runs and their structured failure diagnostics.

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 explicitly tells the agent when to use it (polling a research run) and provides critical guidance on interpreting results: a running run with phase 'initializing' and large elapsedSeconds is stalled and should be reported rather than waited on. It also explains the retryable field semantics, telling the agent when retrying is safe and when to fix inputs or report. This is actionable usage guidance beyond mere description.

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