Chat Status

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

Annotations only declare readOnlyHint=true and destructiveHint=false. The description goes well beyond them by enumerating per-task states (pending/completed/failed/unknown), their sub-states (queued vs generating), the timing fields (queued_s/generation_s), the error object shape, batch ordering behavior, and the 64-id cap. This is exactly the behavioral detail an agent needs and cannot get 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?

It is long, but the length is justified by two distinct modes and four status classes. It is front-loaded with the mode summary and uses headers and bullets to structure the detail. Slightly heavy, but nearly every sentence carries substantive information.

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 3-optional-param tool with two modes and an output schema present, the description covers both modes, all parameters, return shapes, and error handling. Even though the output schema exists, it explains return structure usefully. Nothing an agent needs to call it correctly is missing.

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 0%, so the description must carry the load, and it does: task_id accepts a single id, a list, or a comma-separated string; notebook is the alternate mode selector; conversation_id is optional and defaults to the notebook's most-recent conversation. It also documents the divergent return shapes (single dict vs {"tasks": [...]}) per input type.

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 opening line states a specific verb+resource with two distinct scopes: 'Poll detached asks, or inspect a notebook's live generation session.' This clearly separates it from siblings like chat_ask, chat_start, and studio_status. An agent can identify the tool's function without opening the schema.

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 strong operational context: re-invoke every ~20-30s while pending, polling never restarts a generation, at most 64 ids per call, and that the two modes are mutually exclusive. It also routes the agent by outcome (retriable failure -> one chat_start retry; unknown -> chat_start again). It stops short of explicitly naming alternative tools in a 'use X instead' form, so it does not reach the top tier.

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