Close document

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

Despite destructiveHint=true already being in annotations, the description adds substantial context: it destroys the working directory, does not seal a receipt, refuses on non-empty journal unless discard is set, and explains why (throwing away the accountability record). This goes well beyond the annotation.

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 sentences deliver the primary behavior, the guard condition, the escape hatch, and the rationale. There is no filler, and the most important destructive consequence is front-loaded.

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, conditional tool with an output schema and annotations, the description covers the action, the destroyed resource, the refusal condition, the override flag, and the reason for the safeguard. An agent has enough to decide when to call it and what will happen.

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 carries the parameter-meaning burden. It clearly explains discard semantics in context. session_id is not elaborated, but its meaning is obvious from the tool name and title, so this is only a minor gap.

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?

The description uses a specific verb+object structure: 'End a session and delete its working directory WITHOUT sealing a receipt.' This clearly distinguishes close_document from commit_document, which seals a receipt, and from other sibling operations like open_document or delete_paragraph.

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?

It provides clear context for when the tool will refuse to operate ('when the journal holds recorded operations') and when to set discard. It does not explicitly name sibling alternatives, but 'WITHOUT sealing a receipt' implies the contrast with commit_document.

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