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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description still adds substantive behavior — deterministic serialization rules, float rejection, signature-field stripping, and a SHA-256 side output. It is consistent with the annotations (a pure computation) and adds context beyond them, though it says nothing about failure modes on invalid input.

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 sentences, no filler, but the first is a long subordinate-clause fragment that front-loads the return value rather than the action, making it slower to parse than a 'Canonicalize the object, excluding sig fields' opening would be.

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?

With an output schema present, the description does not need to spell out return values — yet most of its text describes exactly that, while leaving the `exclude` semantics and error behavior unaddressed. Adequate for a two-parameter pure function, but not fully covering the schema gap.

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%, so the description carries the burden. It partially compensates: it clarifies that `object` is the structure being canonicalized and that signature fields are excluded by default via `sig`, which effectively documents the `exclude` parameter's default. It never explains the `exclude` type/format or whether supplying it replaces or extends the default.

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 exact transformation (recursive key sorting, compact encoding, UTF-8, no floats, signature fields stripped) and the accompanying SHA-256, which is enough to distinguish it from verify_object. It is phrased as a noun fragment describing the output rather than 'Canonicalize X', so the operation must be inferred, but the substance is specific.

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 second sentence gives real workflow guidance: sign the returned bytes with Ed25519 and place the base58 signature in `sig`, which implies this is the pre-signing step of a publish/verify flow. However, it never says when to use this versus verify_object, nor states any precondition or exclusion.

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