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

Annotations only say readOnlyHint=false and destructiveHint=false; the description supplies the far more consequential context: the call queues a pending change requiring human approval via the approvalUrl field, the agent cannot self-approve, and the resulting Xero object starts as a DRAFT. It also discloses a hard regional limitation the annotations cannot express. No contradiction with the annotation set.

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?

Front-loaded with the core fact (drafts a proposal, does not touch Xero) and every sentence carries real information - regional refusal, approval gate, ID provenance, draft state, next step. Some redundancy ('does NOT touch Xero itself, and never will on its own') and a single dense paragraph cost it the top mark.

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?

For a two-parameter mutation tool with no output schema, the description covers everything an agent needs: what is created, what state it lands in, who must approve, where the approval link lives, the regional restriction, and the follow-up tool. Nothing material is left to inference.

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 coverage is 100%, so the baseline is 3; the description earns above that by explaining the negative space - Xero computes period start/end and payment date from the calendar, so those parameters are deliberately absent - and by reinforcing the provenance rule for payrollCalendarId. It adds meaning rather than restating the schema.

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?

States a specific verb and resource ('Proposes a DRAFT pay run for one payroll calendar') with scope (AU/NZ orgs) and immediately distinguishes it from the write-side sibling by noting it does not touch Xero itself. Read alongside list_xero_pay_runs and post_xero_pay_run in the sibling list, an agent can pick correctly without opening a schema.

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?

Explicit when-not-to-use ('Refuses plainly for the United Kingdom' with the reason), explicit prerequisite (payrollCalendarId must come from list_xero_payroll_employees, never invented), and explicit hand-off to post_xero_pay_run as a separate irreversible step. Alternatives and exclusions are both named, not inferred.

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