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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the bar is lower. The description still adds real context beyond them: 'Nothing is changed and no model runs' rules out inference side-effects, and 'authenticated when sealed and admitted under book law first' discloses a validation gate that could cause rejection.

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?

Input mechanics are front-loaded in the first paragraph, which is good, but the opening clause 'a book keeps its entries, and every balance follows from them' is ornamental and the 'book law' phrasing is vague. The second paragraph re-describes the output already captured by the output schema.

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?

With an output schema present and 100% parameter coverage, the definition only needs to convey scope, inputs and safety, all of which are covered. The remaining gap is routing guidance against the many sibling reporting tools, which matters given the crowded namespace.

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 schema already documents all four parameters, including the book/handle exclusivity and as_of default. The description restates accepted handle payloads (sealed package, book body, {book, annotations}) and the as_of meaning but adds little beyond the schema text, matching the baseline 3.

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+resource: derives the trial balance and general ledger of one Standard Books document from its journal entries. An agent can tell this is a reporting/derivation operation, but the description never names or contrasts with near-neighbors like generate_trial_balance, generate_report, or audit_standard_book, so the sibling distinction is left implicit.

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?

Gives input guidance (use a transfer handle for a full book, inline `book` only for a small one) and clarifies admission rules, but never says when this tool is the right choice versus generate_trial_balance or generate_report, nor any exclusions. Usage is implied by the input shape rather than stated.

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