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

Beyond the readOnlyHint annotation, the description discloses that the response includes a progress field with phase/message/counts when available, that health_score and issues_found are sourced from the published report matching get_report's summary, and that health_score is null for blocked/unreachable sites. This is significant behavioral context not inferable from 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 organized by status outcomes, with the core polling instruction first and edge cases after. Each sentence carries distinct information—status transitions, progress field, report equivalence, null behavior—with no redundancy or filler.

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?

With no output schema, the description carries the burden of explaining return semantics, and it does: it defines all statuses, the progress field, the meaning of health_score/issues_found, and the null case. It also tells the agent the next action (get_report) for completed runs, making the tool fully usable.

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 100% and both schema and description state that run_id comes from run_audit or list_audits. The description adds no new parameter-level detail such as format, constraints, or examples; it only frames the parameter in the polling workflow, which is already the tool's purpose. Baseline 3 applies.

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 opens with a specific verb ('Poll') and resource ('a running audit by run_id'), and immediately scopes the run_id source to run_audit or list_audits. It clearly differentiates this status-polling tool from siblings like get_report by stating when the report is ready.

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 explicitly explains the polling loop: pending/running means keep polling every 15-30 seconds, completed means call get_report with the same run_id, and failed/cancelled includes error/reason. This gives an agent both when to use the tool and when to switch to an alternative.

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