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

Annotations already establish readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safe-read profile is covered. The description adds genuinely useful behavior beyond that: this is a polling endpoint, it terminates on terminal=true, and success requires the conjunction of verdict=clean, coverage_complete=true, and result_consistent=true. It does not mention rate limits, backoff, or what happens after terminal, keeping it short of a 5.

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, zero filler, front-loaded with the action and polling mechanism, then the success condition. Every clause earns its place and nothing is repeated from the schema or annotations.

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 an output schema exists, the description does not need to explain return fields, and it correctly focuses on the decision logic (terminal, verdict, coverage_complete, result_consistent, next_action). For a read-only polling tool with full schema coverage and annotations, this is nearly complete; only the absence of guidance on polling cadence, timeout, or what next_action can contain keeps it from a 5.

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 only parameter is run_id, and the schema already documents it fully at 100% coverage (including that it comes from verify_document). The description adds the polling parameter poll_after_ms, which is behavior-adjacent rather than a declared input, but that is bonus information rather than required semantic fill-in. Baseline for a fully documented single parameter is high.

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 action ('Poll a run') and names the artifact being read back ('verification run' per the title), which is enough for an agent to identify it. It does not explicitly contrast itself with siblings like get_pack_build_status or verify_document, so an agent must infer the distinction from the run_id parameter and the Vera/verification framing.

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?

It gives actionable polling guidance ('using poll_after_ms until terminal=true') and a decision rule for declaring success versus following next_action. It stops short of stating when not to call it or what the alternative tools are, so it is clear context without full exclusion logic.

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