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

Annotations already declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is largely covered. The description adds useful context beyond that: the 65536-byte request cap, 5 s execution time, and 'candidate only when verified' conditionality. These are genuine behavioral details, though several (idempotency, non-destructiveness) are already in annotations.

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 label-based format (Problem/Input/Result/Limits) is telegraphic and fragmented rather than front-loaded prose. The 'Input:' line trails off with '...' and mixes object contents with parameter names. Reads as compressed notes, not a coherent definition.

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 tool with nested objects, four required params, no schema descriptions, and 65536-byte/5 s limits, the description is under-specified. Having an output schema mitigates the need to explain return values, but the input contract remains opaque and no usage guidance anchors it against ~20 siblings.

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 0% and four required parameters (schema_version, request, idempotency_key, max_total_price) have no descriptions anywhere. The description only lists generic input concepts ('supported controller, current gain, fixture error, target error') that do not match the actual parameter names, leaving the request payload structure unexplained. Does not compensate for the coverage gap.

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?

States a clear verb (tune) and resource (controller) constrained to objectives, distinguishing it somewhat from siblings. However, the 'supported controller' phrasing is vague and the sentence is fragmented into Problem/Input/Result/Limits labels rather than a clean purpose statement. Enough to identify the tool but not sharp.

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?

The description never states when to use this tool versus the many robotics_* siblings like robotics_optimize_disturbance_rejection_v1 or robotics_compare_controller_responses_v1. The 'Limits' line gives scope constraints (software/model evidence only) but no positive usage guidance or alternatives.

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