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

Goes well beyond the destructiveHint annotation by disclosing the merge lifecycle: names resolve to builds, the merged build is polled, terminal status is reported, and error/zero-screenshot outcomes surface as tool errors rather than success. Critically warns that the merged build takes the baseline flag, so a failed merge leaves the baseline on an empty build — a non-obvious destructive consequence.

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 sentences, front-loaded with purpose and the read alternative before behavioral detail. Dense but every clause (polling, error semantics, baseline-flag side effect) carries information an agent needs. Slightly packed, but no waste.

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 destructive, multi-mode mutation tool with no output schema, the description covers what the tool does, when to use it vs the read sibling, how success/failure is signaled, and the lasting state change. Nothing an agent needs to call it safely is missing.

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% (baseline 3), but the description adds meaning: source/target are names that get resolved to builds, and merge_branch vs merge_build reinterpret those same fields as branches or build names. This clarifies the enum-conditional parameter semantics beyond the schema text.

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 (merge) and resource (SmartUI baselines) with scope (across branches or builds), and explicitly distinguishes itself from the read-path sibling smartui_project_query. An agent can identify this as the mutation counterpart to the SmartUI query tools without opening a schema.

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 routes the agent: 'to read baseline settings, use smartui_project_query with action=get', and names the two merge modes (merge_branch/merge_build) with their distinct source/target semantics. When-to-use and the alternative for the read case are both stated.

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