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

The annotations already declare readOnlyHint=true and destructiveHint=false. The description adds useful context beyond annotations: the polling interval, the loop guidance, and the condition to stop polling (status is 'done'). While it doesn't detail possible error states or return-field formats, it provides meaningful behavioral guidance.

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 three short sentences, each adding value: the action, the next step after completion, and the polling cadence. No filler or repetition; a front-loaded and efficient example.

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 single-parameter polling tool with no output schema, the description is mostly complete: it explains the dependency on start_trace, the next step (read_report), and implies a status field by referencing status. It could explicitly list potential statuses or error behavior, but the description is fully usable for an agent.

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 coverage is 100% and the job_id parameter's description reads "Job id returned by start_trace." The tool description adds little beyond the schema, simply implying that the trace was created with start_trace. Since the schema already carries the semantic weight, the baseline score of 3 is appropriate.

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 and resource: "Poll a trace started with start_trace." It clearly identifies what the tool does and distinguishes it from siblings like start_trace and read_report. The follow-up instructions about read_report reinforce the intended role.

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 explains when to use this tool (to poll a running trace created by start_trace), when to move to read_report, and how to poll responsibly ("Poll every 10-15s, not in a tight loop"). This gives concrete usage guidance and names the relevant alternative for the next step.

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