billcom_list_bills

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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: the effect parameter is required and must be 'read' with Spring verification, pagination has bounded defaults, and approval_ref is disclosed as an "Approved platform task UUID when resuming a write," hinting at participation in resumable write flows. No contradiction with annotations.

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 one-line purpose statement is front-loaded and every Args line is compact and informative. Minor redundancy exists: 'effect: Required' repeats the schema's required array and const value, which slightly weakens efficiency, but overall there is no filler and the structure is scannable.

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?

Given the output schema exists (so return format need not be explained), annotations cover the safety profile, and the description covers purpose, both invocation modes, pagination defaults, and all parameters, this is nearly complete for a read tool. The only gap is that the 'resuming a write' behavior behind approval_ref is cryptic and unexplained, though it is at least disclosed.

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 description coverage is 0%, so the description carries the full burden, and it compensates well by documenting all 9 parameters with semantic value: defaults (start=0, max=100), bounds (max 1-100), the exclusivity rule for id vs page, and role descriptions for project_id, connector_account_ref, idempotency_key, and approval_ref. Some entries are terse but are not tautologies.

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 opens with a specific verb+resource: "Read one Bill.com bill by id, or one bounded page of bills." This precisely distinguishes the tool from write-oriented siblings like billcom_create_bill and billcom_approve_bill, and from other-resource list tools like billcom_list_payments and billcom_list_vendors. The dual-mode scope (single id vs bounded page) is explicit.

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 gives clear usage context: use id for an exact bill, or start/max for paging, with the explicit constraint that "id cannot be combined with a page." Defaults and bounds (start default 0, max 1-100 default 100) tell the agent how to invoke each mode. It does not explicitly name alternatives or exclusion conditions, but the read-mode context is unambiguous.

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