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

Even though annotations already declare the tool read-only and idempotent, the description adds crucial behavioral details: ops apply in order, are all-or-nothing, the first failing op stops the batch, and the input is left untouched. It also specifies the exact error shape and that `opIndex` indicates the failing op. No contradiction with 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?

Every sentence contributes unique information: purpose, relationship to `execute`, usage guidance, return/error behavior, and op format. The description is detailed but tightly structured, front-loaded with the core purpose and followed by necessary qualifications.

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 no output schema, the description fully specifies success and failure return shapes, the meaning of `opIndex`, and the all-or-nothing behavior. It also references `describe_sdk` for op signatures, making it complete for a complex mutation tool with a generic item schema. Sibling tool distinctions are clearly handled.

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?

The schema only defines `source` and `ops` generically, but the description adds essential semantics: each op is `{ kind, ...fields }`, ops are ordered, and the batch is atomic. It also explains how the parameters relate to the output and error handling, going well beyond the schema's coverage.

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 leads with a specific verb and resource: 'Apply a list of structured edit ops to an existing Mermaid source and return the edited diagram.' It clearly distinguishes itself from the sibling `execute` by calling itself the declarative counterpart, making its role unambiguous.

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?

Explicit guidance is provided: prefer `mutate` for straightforward edits and reserve `execute` for logic the ops don't express. It also advises calling `describe_sdk` before authoring unfamiliar ops, giving clear when-to-use and when-not-to-use instructions.

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