document_close

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

With no annotations, the description carries the burden well: it discloses the validation rule (exactly one of save_changes/discard_changes), the failure mode (INVALID_PARAMS, document stays open), and the prerequisite that save_changes requires a previously saved document. It stops short of saying what happens when closing the last open document or that discard is irreversible.

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 invoking condition is front-loaded in the first sentence, followed by the constraint, the return shape, and a one-line example. Every line serves a purpose, though the example is marginal and the return shape partially repeats the schema's semantics.

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?

No output schema exists, so spelling out the return payload is appropriate and useful for chaining (the new active document). Failure semantics and the save precondition are covered; only edge cases like closing the final document are unaddressed, which is minor for a 3-optional-parameter tool.

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 per-parameter meaning is already documented. The description adds a genuine cross-parameter constraint not expressible in the schema — exactly one of the two boolean flags must be true — plus the saved-document precondition for save_changes, which is real value beyond the schema.

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?

Names a specific verb and resource ('close the document') and makes the triggering condition unambiguous. It implicitly separates itself from document_save by routing saving to that tool first, but does not explicitly contrast with document_activate or document_open.

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?

States an explicit gate ('Call ONLY when the user explicitly asked to close the document'), names the alternative to use first ('call document_save with a name first'), and gives the failure outcome if flags are misused. An agent has no ambiguity about when to reach for this versus its siblings.

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