apple_keynote_close

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

Annotations only say this is a destructive, non-idempotent, non-read-only operation; the description goes further by disclosing the two refusal conditions (unsaved changes, no saved path) and the discardChanges override, which tells the agent exactly what is at risk. This is exactly the 'what gets destroyed' context that annotations cannot express.

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 the core action front-loaded and the constraints following; every clause carries information (verb, refusal conditions, override, alternative). The semicolon-joined second sentence is slightly compressed but not 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 two-parameter destructive tool with no output schema, this covers the essential decisions: how to identify the document, what blocks the close, how to force it, and how to preserve changes. It stops short of describing post-close state (e.g., whether the app or window remains open), but nothing critical for invoking it correctly 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 50%: documentName is documented in-schema with the list_documents lookup guidance, while discardChanges has no schema description. The description compensates for that gap by explaining discardChanges:true as the override that forces the close past the unsaved-changes refusal, adding meaning beyond the bare boolean default.

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 with scope ('Close one Keynote document'), and implicitly separates itself from apple_keynote_save by noting that saving must happen separately. It is clear and unambiguous, but it never names the sibling tools that an agent might confuse it with (save, export), so it falls short of full sibling differentiation.

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?

Gives a real decision rule: if you want to keep changes, call save first rather than closing, and discardChanges:true is the escape hatch for unsaved work. It lacks an explicit 'when not to use' clause or any mention of documents that were never saved to disk from the user's perspective, but the routing to the save path is clear.

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