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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'Writes nothing' partly restates the safety profile. The added value is the eligibility constraint (requires a trusted rendered prompt snapshot) and the fact that the return is a unified diff, which the annotations do not convey.

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 tight sentences with zero filler, and the core action (preview a diff) is front-loaded before the eligibility caveat. Every clause carries information.

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 read-only preview tool with fully documented parameters and no output schema, the description covers what the tool does, the eligibility precondition, and the nature of the return value. Only minor gaps remain (e.g. nothing about size limits for very large prompts).

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 100%, so every parameter including customerId, conversationId, and proposedPromptContent is already documented in the schema. The description adds no extra syntax, format, or constraint detail beyond the schema, making the baseline 3 appropriate.

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 (Preview) and a precise resource (a read-only unified diff between the trusted prompt snapshot used by a run finding and proposed prompt content). No other sibling tool previews a diff, so it is unambiguously distinguishable from get_run_finding_context, validate_variant, and apply_variant.

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 description supplies a real precondition - it 'only works when the run has a trusted rendered prompt snapshot' - which tells the agent when invocation is valid. It stops short of naming alternatives (e.g. validate_variant or applying the change) or stating an explicit when-not, so it falls short of a 5.

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