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

The BEHAVIOUR section goes well beyond the annotations by specifying 'pure deterministic calculation — no side effects, no network or storage access', idempotence, and exact error behavior for division by zero or non-finite inputs. This provides valuable safety and execution clarity. The description aligns perfectly with the readOnly, idempotent, and non-destructive hints.

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 well-structured with labeled sections (FORMULA, WHEN TO USE, WHEN NOT TO USE, BEHAVIOUR, RETURNS, PARAMETERS) and front-loads the core meaning. It is longer than strictly necessary and repeats some annotation and schema information, but the organization keeps it scannable and useful.

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 purpose, usage context, behavioral guarantees, return shape, and most parameter semantics. It lacks a complete parameter listing in the text, but the rich input schema fills that gap. The output is described adequately even without an output schema.

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?

Although schema coverage is high, the description's PARAMETERS section is misleading: it lists only net_credit_sales and begin_receivables as required and completely omits end_receivables, despite three required parameters. It also gives the formula 'DSO = 365 / Receivables Turnover' without explaining how the inputs translate into receivables turnover. This partial and incomplete parameter explanation can mislead an agent about required inputs.

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's function with a specific verb and resource: 'Calculate days sales outstanding (DSO): the average number of days it takes a company to collect payment after a sale.' It is distinct from the sibling turnover calculations because it focuses on collection speed and DSO. However, it does not explicitly name or contrast itself with any sibling tool, so it falls just short of full differentiation.

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 provides explicit 'WHEN TO USE' and 'WHEN NOT TO USE' sections, including a concrete condition to avoid using the tool (mixed cash/credit revenue). It does not name specific alternatives, but it gives clear context for when this metric is appropriate. This is strong guidance, though not as complete as naming sibling tools.

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