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

Beyond the annotations (which only say not-readOnly, not-destructive, not-idempotent), the description discloses refusal conditions and who they name, the effects list (file built, hand-over recorded, link minted), retention with control totals and a hash, and a handling rule ('never relay the file's bytes'). This is exactly the mutation context annotations cannot carry.

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?

Front-loaded with the action and effects summarized at the end in a scannable 'Effects:' line. Slightly mannered phrasing ('Hand the period over', 'the act that says the period has been handed over') adds words without adding precision, keeping it off a 5.

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 non-idempotent write with no output schema, the description covers what is produced (a download link, not bytes), what is persisted for later audit, and what blocks the call. Nothing an agent needs in order to call 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 100%, so the baseline is 3; the description earns a step above by explaining the consequence of omitting 'from' ('month-end becomes a diff, not a re-key') rather than just restating the schema. The multi-currency requirement for 'currency' is left to the schema, so it is not a full 5.

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 clause names a concrete verb and resource ('build the file in the ledger's shape', 'return a download link') and immediately distinguishes itself from the sibling that only previews (bridge_preview). An agent can tell this is the committing export act versus bridge_preview and bridge_exports without opening schemas.

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?

Explicit ordering rule ('Show the person bridge_preview and its totals first'), an explicit variant of the call ('Omit "from" to continue from the last hand-over'), and an explicit precondition ('Refused while an account the period uses is unmapped'). When-to-use, how-to-vary, and when-it-fails are all stated.

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