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

With readOnlyHint=false and destructiveHint=false annotations, the description adds crucial context: without apply it only shows the plan; with apply: true it rewrites the working copy in place, and undo_last_change can revert it. This goes beyond annotations by disclosing the preview/edit distinction and reversibility, though it doesn't mention permissions or rate limits.

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 description is reasonably concise, front-loading the usage scenario, then explaining dry-run vs. apply behavior and recovery. It could be slightly tighter but every sentence contributes to understanding the tool's dual mode.

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 tool with no output schema, two parameters, and partial schema coverage, the description provides enough context: what the tool does, when to use it, what the plan shows, and how apply and undo work. It doesn't elaborate on the output of the plan or error conditions, but covers the essential decision points.

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 50%, with only 'formula' documented in the schema. The description compensates by explaining the apply parameter's semantics: absent/false shows the plan, true applies the rewrite in place, and undo_last_change reverts. This adds meaning beyond the schema for the undocumented 'apply' parameter.

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?

States a specific verb (rebuild/formula) and resource (formula using shelf materials), and clearly distinguishes it from siblings like find_substitutes or use_substitute by describing the full-formula replacement plan and the app's 'Replace with materials I own' feature.

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?

Explicitly names the trigger: 'Use this when the user asks what they can make with the materials they own, or wants a formula rebuilt using only their shelf,' and contrasts the dry-run vs. apply behavior. It also names undo_last_change as the recovery path, giving when-to-use and when-not-to-apply guidance.

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