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

Adds real behavioral context beyond the destructiveHint annotation: no customer notification, no income posting until sent, and the draft is editable/discardable in FreeAgent. This meaningfully clarifies the side-effect profile, though it doesn't note auth requirements or response behavior.

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?

Three tight sentences, front-loaded with the core action and state, then the behavioral caveat, then the API mapping. No wasted text and nothing buried.

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 creation tool with no output schema and fully documented params, the description covers the important state semantics an agent needs. It could say more about auth/scopes or the returned draft identifier, but nothing essential is missing for correct invocation.

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 100%, so every parameter (contact, dated_on, payment_terms_in_days, invoice_items, etc.) is already documented in the schema. The description adds no parameter nuance beyond that, so the baseline 3 applies.

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, resource, and lifecycle state: 'Create a sales invoice in DRAFT status.' This cleanly distinguishes it from siblings like freeagent_list_invoices and freeagent_get_invoice without the agent needing to open any 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?

Explains the operative context: a draft is not sent nor posted as income until marked sent, and can be edited or discarded. That tells the agent what kind of invoice it is producing, though it stops short of naming explicit when-not conditions or alternative tools.

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