xero_list_folders

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

Annotations already provide readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the core safety profile is covered. The description adds one context line about governed connector authority and notes that effect must be 'read' and Spring verifies it. However, it doesn't explain behavior such as return format, pagination, or what an agent can expect from listing folders.

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 compact and mostly structured as a list of parameters in a scannable block. It front-loads the platform identity and governing constraint before the args list. The routing sentence earns its place; only a little extra domain context would be needed to push it to 5.

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?

An output schema exists, so return-value documentation is not required. Yet for a list operation on a governed connector, the description does not explain what data is returned beyond the name 'folders', nor how to get useful folders from Xero. It does state crucial governance constraints (exact project/account authority, effect read) which is valuable. But given the presence of many sibling list operations and the operation-specific arguments JSON, the description leaves some selection and invocation uncertainty.

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 burden, but it only paraphrases parameter names (arguments, project_id, project_ref, connector_account_ref, idempotency_key, effect, approval_ref) without explaining how they interplay. The line 'effect: Required and must be read; Spring verifies it' adds one meaningful detail, and 'approval_ref... when resuming a write' clarifies when that ref is needed. Still, the core `arguments` JSON blob semantics and project/connector resolution mechanics are left to the agent to infer.

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 identifies this as the Xero connector operation `list_folders` (platform tool `xero.list_folders`), naming the specific verb and resource. It doesn't confuse with siblings because the name already conveys listing folders, but the description fails to state what folders are being listed in Xero (folders in Files? Projects?) or provide any domain-level detail beyond the platform operation label.

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 states it 'Routes only through the exact project/account governed connector authority,' which implies tightly-governed routing, but gives no guidance on when to select this tool versus the many sibling list operations (e.g., xero_list_projects, xero_list_files). No explicit alternatives or exclusions are provided.

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