dm_2d_analyze

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

With no annotations, the description carries the full load and does disclose real behavioral traits: it writes multiple artifact types into a new directory, requires that directory not pre-exist, uses operation_id + result_dir for later lookup, and critically states it does not automatically rerun tasks in an uncertain state. That last point is valuable idempotency/failure-handling context. Missing are runtime/long-running expectations and failure modes.

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 optionality caveat is front-loaded and each sentence carries distinct information (scope, outputs, prerequisite, alternative, state semantics). It is dense but not padded; the only mild weakness is that the closure on operation_id/result_dir feels appended rather than integrated.

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 6-parameter tool with a nested object and no output schema, the description compensates well by enumerating what gets written (numerical values, plots, report, rerun script). The remaining gap is capture_dir's expected contents and whether the call is synchronous, but an agent has enough to invoke it correctly.

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 description coverage is 50%; roi, top_n, and the profile endpoints are already documented in the schema, so the description needn't repeat them. It does add meaning to operation_id and result_dir (their role in querying/state tracking), but capture_dir and the profile.width field are unexplained in both places, so the gap is only partially closed.

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 concrete operations (combined statistics, profiles, full FFT on the captured package) and the artifacts produced (values, figures, report, rerun script), which is a specific verb+resource statement. It implicitly separates itself from the single-purpose siblings by noting simple measurements should use individual tools, though it never names dm_stats/dm_profile/dm_fft directly.

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 explicitly states this is optional and not a required DM step, gives the condition for preferring alternatives ('simple measurements → use individual tools'), and adds an environmental prerequisite (needs an independent report environment). What it lacks is naming which sibling tools to use instead, leaving the agent to infer the mapping.

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