cw_markers

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

With no annotations, the description carries the full behavioral burden, and it only discloses that the dialog 'IS writable, unlike SONAR's own controls.' It does not say whether calling the tool opens a UI, runs a command, mutates the project, or what state is affected — the mutability hint is partial credit at best.

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 sentences, no padding in length, but the lead clause 'Everything about markers' is vague and the second sentence is internal jargon about MFC dialogs and 'drawn surfaces' that does not help an agent act. Front-loading is fine; the substance is thin.

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?

No parameters, no annotations, no output schema — so the description must explain what a call does and what comes back. It only gestures at 'the dialog, the commands, and how to read the marker list back' without saying what the response contains or what side effects occur, which is not enough for a tool with this much framework-specific behavior.

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 the schema carries all parameter meaning and the baseline of 4 applies. The description does nothing to obscure that, though it also adds nothing on invocation shape.

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 names the topic (markers: the dialog, the commands, reading the marker list back), so the resource is identifiable, but it never states a specific operation or what calling the tool returns. 'Everything about markers' plus a design-pattern aside reads more like documentation prose than a tool definition, and it does not distinguish it from siblings like cw_ui_recipe or cw_command_support.

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 statement of when to use this tool versus alternatives. The phrase 'this is the working pattern for a drawn surface that has a command opening an MFC dialog' hints at a use case but never says what the agent should call it for or when not to.

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