list_roles

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

No annotations exist, so the description carries the full burden, and it does disclose the return shape in detail: workspace, sandbox profile, engine/model/effort binding, binding:null semantics, and the 'seats' expansion for list-bound roles. It adds genuinely useful context, but it omits any statement of read-only safety or permission requirements, and the sentence structure makes the behavior hard to extract.

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 description is a single dense, grammatically awkward run-on ('the engine, model and effort .cross-agent/config.json binds it to') that buries the key fact under convoluted phrasing. It is not front-loaded with a clear statement of what the tool does, and the sentence is hard to parse on first 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?

With no output schema and no annotations, the description must supply the return semantics, and it does attempt to describe the role/binding/seat structure in full. However, the explanation is confusingly worded and omits the read-only nature and any usage context, leaving the agent with an incomplete picture for a tool whose only purpose is its output.

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 clarify; per the rubric a 0-parameter tool earns a baseline 4. No parameter information is missing.

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 name list_roles is clear, and the description implies it returns the roles of the active mode along with their workspace, sandbox profile, and engine/model/effort binding. However, it opens with a noun fragment ('The roles the active mode has:') rather than a verb+resource statement, and it never distinguishes this tool from siblings like describe_mode, so the purpose is inferable but not stated.

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?

There is no explicit when-to-use guidance, no prerequisites, and no comparison to alternatives such as describe_mode. The only indirect routing hint is the note that a null binding is 'the engine a delegate call must name itself,' which gestures at delegate but does not tell the agent when to call list_roles.

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