list_uvision_instances

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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description reveals the non-single-instance behavior of UV4.exe, potential instance accumulation, the note generated when count>1, and rejection of unrecognized parameters. This is meaningful behavioral context not otherwise available.

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 long but efficiently ordered—purpose first, then use case, parameter details, and aliases. The anecdote about six instances is slightly extra but reinforces the problem domain. Every sentence contributes; there is no filler or redundant restating of the schema.

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?

Given that an output schema exists, the description covers the returned fields (PID, start time, project, window), the note behavior when count>1, and the optional projector filter. It also references the follow-up action close_uvision. This is sufficient for an agent to understand the tool's behavior and interpret its results.

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 0%, so the description fully compensates: it defines the optional project parameter as a filter on the opened project, lists accepted aliases (path/proj/project_file/project_path/uvprojx), and explicitly states that unspecified parameter names are rejected. This gives the agent complete guidance for correct invocation.

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 states a specific verb+resource: list all current Keil uVision instances with details (PID, start time, opened project, window presence). It also explains its purpose—checking for residual duplicate project windows—which distinguishes it from sibling tools like launch_uvision or close_uvision.

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 gives clear context: use when you need to confirm whether multiple project windows remain after repeated launches. It mentions the convergence action close_uvision(keep='latest') when count>1. It doesn't explicitly state exclusions (e.g., when not to use), but the read-only inspection role is implied and clear.

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