close_project

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

Annotations already declare destructiveHint=true and readOnlyHint=false, and the description adds a real behavioral guard the annotations don't convey: the operation fails rather than silently discarding unsaved changes. It still doesn't say whether `save: true` persists to disk or what state the project is left in after closing.

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 action stated first and the failure mode second. Nothing padded or repeated from the schema.

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?

An output schema exists, so return values needn't be described, and the key gotcha (unsaved changes) is covered. For a two-parameter destructive tool it's nearly complete; the missing piece is identifying what `project` accepts and whether close releases the project handle for reuse.

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 0%, so the description carries the burden for both parameters. It fully explains `save` (gates whether unsaved changes are persisted instead of refusing), but `project` — a required string, presumably name or path — gets no explanation at all.

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?

"Close a project" is a specific verb + resource and is clearly distinct from siblings like open_project, save_project, and new_project. It doesn't explicitly contrast itself with save_project (which the same agent might otherwise reach for), so it stops short of a 5.

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 refusal condition ("Refuses if it has unsaved changes unless `save` is true") gives the agent a concrete decision rule for the `save` flag. However it never says when to prefer close_project over save_project, or whether close is required before opening/creating another project.

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