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

Annotations already establish readOnly/idempotent/non-destructive, and the description adds real value on top: the failure surface (no input, unusable taps, bpm outside 30-300, unlisted time signature) and the signal that this is pure arithmetic on supplied numbers rather than audio analysis. It does not cover tap-to-bpm fallback precedence, which the schema handles.

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 dense sentences, front-loaded with the tool's identity and followed by inputs, outputs, and exception cases in call order. The middle sentence is long and carries several clauses, but no sentence is filler.

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?

Output schema exists, so return values need not be re-specified, and the description still names them at a high level while covering both input modes, the output shape, and every documented error condition. An agent can call this correctly without further inference.

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 100%, so the baseline is 3, and the description earns a step up by framing the parameters as mutually alternative modes ('Either way') and restating the accepted bpm window and time-signature constraint at the point where an agent decides how to call it.

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?

Opens with a specific framing ('Tempo arithmetic for editing to music') and then enumerates the concrete outputs: BPM with stability/confidence, beat length, delay table, and bar duration. It also explicitly rules out the misinterpretation ('does not analyse audio'), which no sibling tool covers.

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?

Clearly states the two invocation modes ('pass tap timestamps... or pass a known bpm'), giving the agent an explicit choice criterion. It stops short of naming alternatives, but the sibling tools are unrelated utilities, so there is little to route between.

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