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

The description adds a key behavioral detail beyond the annotations: 'does not save or publish the result.' This is important given readOnlyHint=false, clarifying that while the tool may modify in-memory state, it does not persist changes. It also implies the output is a refined payload. There is no contradiction with the 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?

The description is two concise sentences, front-loaded with the action verb 'Use to refine.' Every sentence earns its place: the first states the purpose and target, the second clarifies a crucial side effect (no persistence). There is no redundant or filler content.

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?

The description adequately covers the tool's purpose and a key behavior for a refinement tool, despite having five parameters and no output schema. It leverages the schema descriptions for parameter details and sibling context for differentiation. The main gap is not explicitly mentioning the return value, but 'refine' implies an updated payload, making this sufficiently complete.

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 100%, so the baseline is 3. The description adds context by naming 'natural-language instruction' and 'previously generated payload,' which maps to the required parameters, but it does not provide additional syntax or constraint details beyond what the schema already offers. No parameter information is missing, but the description does not enrich the parameter understanding.

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 clearly states the tool's function: refining a previously generated Gravity AI UI composed payload using a natural-language instruction. It distinguishes itself from siblings by emphasizing 'previously generated,' aligning with the presence of generate_interface, get_interface, and search_interfaces. The phrase 'does not save or publish' adds a clear boundary for the tool's effect.

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 gives a clear when-to-use context: when you have an existing composed payload to refine. It implies this is not for creating new interfaces (sibling generate_interface) or for retrieval (get/search). However, it does not explicitly state exclusions or name alternative tools, so it lacks the full 'when-not-to-use' guidance.

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