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

Annotations already declare readOnlyHint=true, and the description is consistent with that, adding that no writes persist and enumerating the return content (validation, replacements, bounds, before/after cells). It also clarifies the semantic boundary ('Not a reservation'), which annotations cannot express.

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?

Three short sentences, front-loaded with the core action and each subsequent sentence earning its place by covering behavior, return values, and a key distinction. No 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?

With no output schema, the description usefully enumerates what it returns and confirms no persistence, which is what an agent needs to know for a dry-run tool. Minor gap: it doesn't clarify limits like the maxItems=512 batch size or how 'ops' maps to the payload.

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%: request_id and protect_existing are documented in-schema, but 'ops' and 'builder' are undocumented anywhere. The description's 'identical build payload' implies the ops shape but adds no syntax or format detail to compensate for the gap.

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 and resource ('Simulate the identical build payload') with a clear scope qualifier ('without any persistent writes'). This cleanly distinguishes it from the sibling 'build' tool and from a reservation.

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 phrase 'without any persistent writes' and 'Not a reservation' establish when this is appropriate (dry-run validation before a real build) and rule out one misinterpretation. It stops short of explicitly naming 'build' as the alternative to call afterward, but the context is clear.

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