export_backup

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

Annotations already declare this is a non-read, non-destructive, non-idempotent write, and the description is consistent with that. It adds behavior beyond the annotations: the output is a single full-tree file, the operation is fast ('a few seconds'), and the dump can be re-imported to recover from a botched bulk write. It stops short of stating what the call returns or required permissions.

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 imperative action is front-loaded in the first sentence and the trigger condition follows immediately. The 'cheap insurance' framing is mildly rhetorical but it carries real justification (low cost, high recovery value) rather than padding.

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 write tool with no output schema, the description covers why and when to call it, but does not say what the call returns (e.g., the path of the written file), which is the one piece an agent calling it blind would want.

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 100%, so both dest_path and export_format are already fully documented in the schema, including the never-overwrite rule and format trade-offs. The description adds no parameter-level detail, so the baseline 3 applies.

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 opening sentence gives a specific verb and resource with scope: 'Write a full-tree export to disk.' The scope word 'full-tree' separates it from partial or object-level operations, and no sibling tool performs exports, so the agent can identify it immediately without opening the schema.

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 gives an explicit invocation trigger: 'Take one before any bulk write,' and explains why (a failed bulk write cannot always be undone transaction by transaction). No alternative or exclusion is named, but none exists in the sibling set, so the guidance is actionable even if not framed as a comparison.

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