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

Annotations only say read-only/non-destructive/closed-world; the description goes far beyond them by disclosing the exact return shape `{task_id, status, progress, message, dashboard_url}`, the terminal status values, the conditional `result` field on completion, and the `report_url` surface. That is precisely the behavioral context the annotations cannot carry.

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 first clause is well front-loaded, but the second paragraph is a long run-on enumerating nested `figures.branches` fields and a parenthetical about `start_test`/`offers` that is tangential to reporting progress. Much of that detail would be better placed on the result/summary tool it duplicates (`summarize_workflow`).

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?

There is no output schema, so the description correctly spends its budget describing the returned fields, the terminal states, and how the completed payload relates to `summarize_workflow`. An agent can call and interpret it correctly; only the `task_id` provenance and the division of labor with `get_primitives_run_result` are left unstated.

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?

With a single parameter at 0% schema description coverage, the description must carry the meaning, and it does only indirectly by tying the run to `start_primitives_run`. It never states that `task_id` is the identifier returned by that start call, nor any format or validation constraints.

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?

States a specific verb+resource ('Progress of a lab run') and anchors it to the creating tool `start_primitives_run`. It is clear what the tool does, but it does not explicitly distinguish itself from the very similar sibling `get_primitives_run_result`, which an agent could reasonably confuse it with once status is `done`.

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?

Polling usage is only implied by '`status` reaches `done` or `error`' and by the note that the finished answer carries `result`. There is no explicit 'use this while running, use get_primitives_run_result for the final payload' routing or any guidance on polling cadence, so the agent must infer the workflow.

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