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

Beyond the annotations (readOnlyHint, destructiveHint=false, idempotentHint=false), it discloses the privacy behavior ('key is used only for this call and is not stored'), the billing model ($0.003/call via x402 USDC or card key, first 25 free, failed calls free), and that repeats are not free — which meaningfully reinforces the non-idempotent annotation. This is rich behavioral context that would not be inferable from structured fields alone.

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?

Purpose and algorithms are front-loaded, and the sentences are dense but purposeful, including the billing details and a usage example. The statement 'Reads or computes only and changes nothing' mildly restates the readOnlyHint annotation, and the pricing sentence is long, but nothing is truly wasted.

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 simple three-parameter crypto tool with no output schema, the description covers purpose, parameters, an example, side-effect safety, and cost. The one residual gap is ambiguity about return shape (does it return hex, base64, or both?), which the description only gestures at with 'in hex and base64'.

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, but the description adds a concrete worked example (message=hello, key=secret, algorithm=sha256) showing how the three parameters combine, plus the default algorithm. It also states output encodings (hex and base64), though those are not parameters themselves.

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 (compute) and resource (HMAC of a message with a key) and enumerates the supported algorithms, which implicitly but clearly distinguishes it from the sibling `hash` tool that has no key input. An agent can tell what this tool does and how it differs from keyless hashing without opening the schema.

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 provides a concrete use case ('Use to check webhook signatures'), which is clear context for when to reach for this tool. It does not name alternatives (e.g. use `hash` for unkeyed digests) or state exclusions, so it stops short of the explicit when/when-not guidance a 5 requires.

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