Create chute session

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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds the crucial behavioral fact that this creates a proposal and 'never records any data by itself', plus the explicit confirmation step at the chute. That is exactly the kind of lifecycle detail an agent needs and cannot get from the structured fields.

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 purpose and the never-records-data caveat are front-loaded, and the remaining sentences are information-dense rather than redundant. It is a single long block that could be broken into clearer segments, but nearly every clause carries actionable constraint content.

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 six-parameter creation tool with no output schema, the description covers the mutation lifecycle, the widget vocabulary, ordering rules, and the EID exclusion, which is everything an agent needs to build a valid payload. No obvious gap remains.

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%, but the free-form `options` object and widget `type` enum are only meaningful with the description's catalog: weight uses options.unit, score uses options.min/max with BCS 1-5 defaults, select uses options.choices, treatment uses options.presets, boolean is a yes/no tap. It also supplies arrangement and size ('full'/'half') conventions and a ~6 widget cap that the schema does not encode.

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 first sentence gives a specific verb and resource ('Propose a chute-mode work session') plus the input modality ('from a description of the day's work'), and the second sentence sharpens the scope by clarifying it produces only a PROPOSED session. This clearly separates it from siblings like list_chute_sessions, get_chute_session, and update_chute_session.

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 states the workflow context clearly: propose here, then the user reviews, edits, and starts at the chute. It also gives inclusion guidance ('never add a widget for EID scanning') and a sizing heuristic. It stops short of naming a sibling or stating explicit when-not-to-use conditions, so it is clear context without full routing.

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