cw_probe_state

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

With no annotations, the description carries the full burden, and it does disclose the key trait that the return is a plan/steps rather than live data. It does not state whether the tool is read-only (implied but unstated), what the plan looks like, or what happens on builds where CAKESCRIPT is available. Adequate but thin 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?

Three short sentences, front-loaded with what the tool returns, then what it contains, then the activation condition. No filler and no repetition of schema 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 single optional enum parameter with full schema documentation and no output schema, the description covers purpose, content, and trigger. The remaining gap is what the returned plan actually looks like and whether it is safe/read-only, which would matter since no annotations exist.

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% and the topic enum is documented in detail in the schema itself, so the description does not need to repeat it. The parenthetical fact list (track list, mixer values, notes) loosely mirrors the enum values but adds no syntax or behavioral detail beyond the schema. Baseline 3 is appropriate.

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 description uses a specific verb ('Get a plan') plus the resource it covers ('reading project state on this build') and enumerates the facts it routes (track list, mixer values, notes). This makes clear it returns guidance rather than the state itself, which separates it from data-returning siblings like cw_get_state and cw_list_state. It does not explicitly contrast with cw_surfaces, which appears to be the closest neighbor.

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 names the exact trigger condition ('when cw_get_* tools report CAKESCRIPT_UNAVAILABLE') and the alternative family to try first, which implies the negative case as well. An agent can decide to call this without inspecting any schema.

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