cw_quantize_dialog

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

No annotations are provided, so the description carries the full burden. It does disclose the payload contents (fields, labels, element kinds, accepted values, and 'traps'), which is meaningful. However, it never says whether this is a read-only snapshot, whether the values are captured live from an open dialog or returned as static metadata, or whether any state is mutated — key behavioral facts for an unannotated tool.

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?

Two compact sentences with no filler, and the payload contents come first. The second sentence is design rationale rather than invocation guidance, so it earns its place only partially, and the phrasing is slightly indirect.

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 must describe the return value. It enumerates the kinds of content included but not the shape or granularity (one record per dialog field? a flat map?), and it leaves the live-vs-static question unresolved. Adequate to orient a caller, not enough to predict what comes back.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. Nothing in the schema needs compensating for.

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?

It identifies the resource (the quantize dialog) and what it exposes: every field, accessible label, target element kind, accepted values, and traps. The trailing clause distinguishes it from cw_quantize_plan by explaining it is the raw measurement the plan is built from. The missing piece is a verb — 'as measured' is a noun phrase, and the untranslated CJK term adds friction — but an agent can still tell what it returns.

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 names its sibling indirectly ('kept separate from the plan') and gives the rationale that a caller can inspect the raw measurement rather than the derived plan. That implies the selection condition, but it never says explicitly 'call this before/after cw_quantize_plan' or states prerequisites such as whether the dialog must be open.

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