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

Annotations only declare readOnlyHint=true. The description goes well beyond: it details behavior while running (status only), when complete (compact report with verdict, per-suite results, findings, next_steps), and on failure (cause). It also discloses an important behavioral guarantee: the verdict is honest and never reports 'healthy' if a core suite couldn't run. This adds significant context beyond 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 dense but efficient. It front-loads the purpose, then logically organizes the return behavior: while running, when complete, and on failure. Every sentence conveys necessary information without fluff. The structure flows naturally and avoids redundancy.

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 the tool's complexity (polling with multiple return states) and the absence of an output schema, the description serves as the full spec. It covers all key aspects: running state, completion report contents (verdict, per-suite results, findings, coverage, next steps), and failure behavior. Nothing an agent needs to correctly invoke and interpret the tool is missing.

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?

There is only one parameter, run_id, and the schema already provides a complete description ('The run_id from build_e2e_test.') with 100% coverage. The tool description adds no additional meaning about the parameter itself, so it does not exceed the baseline of 3. The schema carries the semantic weight.

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's purpose: 'Poll an e2e run started by build_e2e_test.' It identifies a specific verb (poll), resource (e2e run), and explicitly references the sibling tool that initiates the run, distinguishing it from other status tools like build_deploy_status. It also describes what it returns during and after the run, leaving no ambiguity about its function.

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 implies usage context by stating it polls a run started by build_e2e_test, making it clear this is a follow-up to that tool. It does not explicitly state when NOT to use it or name alternatives, but the reference to the starting tool provides sufficient guidance. A more explicit exclusion or alternative mention would have earned a 5.

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