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

Beyond the annotations, the description reveals critical behavior: the tool does not touch Xero directly, queues a pending change requiring human approval, and only changes the fields explicitly provided. It also discloses region-specific phone/address behavior and that conflicting phone/mobile values for NZ/UK are refused before drafting.

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 long, but nearly every sentence carries a necessary constraint or warning for a complex, region-sensitive tool. There is some repetition of the 'only fields you provide change' and 'nothing else' ideas, so it is not maximally concise, but it remains well-structured and front-loaded.

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 tool with 8 parameters, a nested address object, region-specific behavior, and an approval workflow, the description covers everything an agent needs: source of employeeId, minimum required fields, partial update semantics, approval URL, region rules, and explicit exclusions. No output schema exists, but the description adequately explains the pending-change result.

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 100%, the description adds essential semantics: partial update behavior ('only the fields you provide change'), the source requirement for employeeId, the AU/NZ/UK phone field distinction, and the fact that state is Australia-only while suburb is New Zealand-only. These meanings go well beyond the raw 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?

The description opens with a precise verb and resource: 'Proposes a change to ONE employee's first name, last name, email, phone/mobile, or home address' and immediately narrows scope with 'STRUCTURALLY NOTHING ELSE' and the AU/NZ/UK organisation qualifier. This clearly distinguishes it from sibling tools like update_xero_contact or update_xero_invoice.

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?

It explicitly tells the agent when to use it ('Provide at least one of firstName, lastName, email, phone, mobile, or address'), where to get required data ('employeeId must come from list_xero_payroll_employees'), and what it cannot do ('This tool has NO field for bank details, tax numbers...'). It also clarifies the approval workflow and that the agent cannot approve the change itself.

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