notebook_run_status

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

With no annotations, the description must carry the behavioral load, and it does disclose a genuinely non-obvious trait: executed[].status 'completed' means orchestration ended, not that every cell succeeded. It also notes 'full' is the default and retrieves outputs. Missing polling cadence/rate-limit/auth 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?

Three tight sentences: purpose first, then the parameter choice, then the status-interpretation caveat. No filler, and the most important gotcha is front-loaded enough to be read.

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?

Covers purpose, parameter trade-off, and the shape and interpretation of the result (executed[].status) despite there being no output schema and no annotations. Only polling cadence/backoff and any auth constraints 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?

Schema coverage is 100%, so the schema already documents both params and baseline would be 3. The description adds rationale beyond the schema, explaining that 'none' is for cheap polling without images and that 'full' retrieves outputs, which helps an agent choose a value.

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: poll a background notebook run, which is clearly distinct from the sibling notebook_run (which starts one) and notebook_run_cancel. It does not explicitly name those siblings, but the operation is unambiguous.

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?

Gives clear context for calling it (poll a background run) and the condition that selects the cheap path: include_outputs='none' for polling without images. No explicit when-not or named alternative, so it stops short of a 5.

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