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

Adds substantial behavior beyond the annotations: the export path is model-backed and metered, typically under a minute, judgment only writes account descriptions/instructions and kinds unplaced accounts, and never sets amounts, dates, accounts or links. It also discloses the self-proving step (book proved against the export's own tables, differences surfaced as errors with evidence) and that the result sits behind a multi-read download handle. The only residual tension is that a 'makes a document' tool carries readOnlyHint=true; the description frames it as derived output rather than mutation of existing records, so this reads as generation rather than a contradiction.

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 outcome and the two source modes, then details per mode — a sensible structure. It is long (four dense paragraphs) and repeats some schema facts such as currency being required with export_handle, but nearly every sentence carries decision-relevant information rather than filler.

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 metered, model-backed generation tool with an output schema, the description covers what an agent needs: which source to supply, what gets refused, what the model does and does not decide, latency, and what the sealed result contains. Return-value detail is a bonus rather than a necessity given the output schema, and the pointer to report_handle closes the loop on follow-up retrieval.

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, but the description adds real semantics: currency is required because 'an export never states it', report files must be added inside the zip, and the two source parameters are exclusive. These restate and reinforce the schema rather than introduce new syntax, so it lands just above baseline.

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 ('Makes one Standard Books document') and immediately defines the artifact as a whole set of books — chart, journal, registers, parties, recorded documents — which separates it from create_standard_chart and create_standard_statements. It also names the two mutually exclusive sources up front, so the agent knows exactly what the tool produces before reading 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?

Explicitly branches on source: export_handle for a QuickBooks Online export (with the requirement that report files go inside the zip and that a bare workbook or CSV is refused) versus chart_id for a workspace-held chart. It also routes the output onward — 'hand it to audit_standard_book, or keep it' — giving the agent the natural next step and the alternative consumer of the result.

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