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

Annotations only cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), so the description must add operational context – and it does. It discloses that processing is bounded, that limits are 8 channels and 4096 samples/channel, and that a round-trip rule is verified, all useful traits beyond the annotations. It does not mention auth needs or cost despite a max_total_price parameter, keeping it from a 5.

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 Problem/Input/Result/Limits structure is front-loaded and each line earns its place by stating purpose, payload fields, output, and bounds. It is appropriately sized with no filler. Minor redundancy between 'Problem' and 'Result' keeps it from a 5.

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?

An output schema exists, so return values need not be explained, and the description does cover purpose, key input fields, and bounds. But for a tool with deeply nested, undocumented request objects and a 0% schema coverage, listing only four field names leaves an agent guessing at the full request shape. Adequate but incomplete for correct invocation.

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% across 4 required parameters, so the description must carry the load. It names relevant request fields (sample rate hz, frequency bins, normalization, rules), which meaningfully documents the nested payload. However it says nothing about the top-level idempotency_key, max_total_price, or schema_version semantics, leaving a real 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?

The description gives a specific verb+resource: 'Convert these bounded frequency bins into time-domain samples' plus an additional round-trip verification step. This is clearer than a name restatement and an agent understands the core operation. It stops short of distinguishing clearly from close siblings such as wave_reconstruct_bounded_capture_v1 or wave_validate_reconstruction_quality_v1, so it lands at 4.

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 frames the operation as a 'Problem' and lists limits, but never states when to choose this tool over the many similar wave siblings or what prerequisites apply. No exclusions or alternative routing are provided. Usage is only weakly implied by the problem framing.

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