company_books

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

With no annotations, the description carries the full burden. It clearly states 'Read-only; nothing writes to the ledger' and explains that the 'record' operation persists under the window, which is a side effect disclosed. It also details the scope and constraints (e.g., period per report, ladder footing, balance sheet balancing, unmapped roles). This is thorough, though it does not cover error handling or edge cases explicitly.

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 description is a single dense paragraph, but it is packed with necessary detail and front-loads the core purpose. It is not overly verbose for the complexity, though structuring operations as a list would improve scannability. Each sentence contributes information, so it earns a high score.

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?

The description covers the main functionality and constraints, and an output schema exists for return values. However, it leaves several parameters (now, engine, entity_ref) unexplained and does not specify how they interact with the operations. For a tool with 7 parameters and no schema descriptions, this is incomplete, though it provides substantial context for the core behavior.

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?

The schema has 7 parameters with 0% description coverage. The description compensates partially by explaining payload_json (sources, window) and listing operations. However, it does not explain now, engine, entity_ref, or how they affect behavior. Given the low coverage, more explicit parameter guidance is needed, but the description adds meaningful context for key parameters.

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 clearly states the tool reads the company's books from the ledger, enumerating specific financial items (income statement, balance sheet, margin ladder, etc.) and explicitly lists operations (build, record, list). It distinguishes itself from siblings like company_costs or company_receivables by focusing on the ledger as the sole source and aggregating multiple readings.

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?

The description explains what the tool does but does not explicitly state when to use it versus alternatives such as company_costs, company_receivables, or company_reviews. There is no mention of exclusions or alternative selection criteria, leaving the agent to infer usage from the scope. Implicitly it is for comprehensive ledger reading, but explicit guidance is missing.

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