freshbooks_list_records

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

Beyond the readOnlyHint annotation, the description adds the return format ('Returns items plus page/pages/total') and the important gating behavior ('Some resources are gated by plan or account role and will report that rather than returning rows'). This provides meaningful behavioral context without contradicting 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 description is front-loaded with the core purpose and follows with return and gating information in separate sentences. The parenthetical list of examples is long but useful for illustrating the long tail, and every sentence adds value. It is slightly wordy but appropriately sized for a generic resource reader.

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 lack of an output schema, the description provides the essential return envelope ('items plus page/pages/total') and the gating caveat. The schema documents the resource and search parameters. It could further explain per_page or variability in resource fields, but it is reasonably complete for a generic list tool.

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 description adds little beyond the schema for parameter semantics. It mentions 'by name' for the resource parameter, but the enum already enumerates resources. The schema lacks descriptions for 'page' and 'per_page', and the description does not explain these pagination parameters or the 'search' object, failing to compensate for the 50% schema coverage gap.

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 'List any FreshBooks accounting resource by name' and identifies it as a generic reader for a long tail of resources, naming many examples. It distinguishes itself from sibling dedicated tools by explicitly covering resources 'alongside the ones with dedicated tools.'

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 sets clear context by calling it 'the generic reader covering the long tail' and listing specific resources, implying this is the tool for those without dedicated tools. However, it does not explicitly instruct agents to prefer dedicated tools for resources that have them, so exclusions are not stated.

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