Closes a design, refusing if unsaved changes exist unless discard_changes is true. Prevents accidental data loss by requiring explicit discard option.
Close a design. Refuses if it has unsaved changes unless discard_changes is true.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | ||
| discard_changes | No |
Changes observed during successful MCP inspections.
v0.2.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already flag destructiveHint=true and readOnlyHint=false, and the description adds real context beyond them: the specific failure mode (refusal on unsaved changes) and the escape hatch (discard_changes). It still doesn't say what happens to the design state afterward or whether the handle becomes invalid.
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 short sentences, zero waste, with the primary action front-loaded and the conditional failure behavior immediately after. Nothing is padded.
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 simple two-parameter close operation with no output schema, the description covers the essential risk (data loss on unsaved changes) and the controlling flag. Only the identity of the 'name' parameter and post-close state are left implicit.
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 0%, so the description must carry the burden. It explains discard_changes well as both a value and an interaction (only needed when there are unsaved changes), but the required 'name' parameter is given no semantic meaning at all in either place.
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 ('Close a design') that an agent can act on immediately. It does not, however, differentiate itself from the sibling close_library, nor clarify the design-vs-library scope distinction present in the tool set.
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 unsaved-changes refusal gives a clear precondition for when the call will fail, which implies usage context (use when finished with a design, after saving). But no explicit alternative is named — save_design and undo exist as siblings and aren't referenced.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.