wafeq_invoices_partial_update

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=false, and the description's '🟡 WRITE · updates data' adds only the HTTP method, which is already visible in the endpoint string. The description omits key behavioral facts: that omitted body fields are left unchanged, whether a FINALIZED invoice can still be edited, and what side effects (e.g., audit, numbering) occur. No contradiction with annotations, but little value added beyond them.

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 short and front-loaded with the write indicator and endpoint, which is structurally good. But it is repetitive: 'updates data', 'Partial update invoice', and 'Endpoint for partially updating an existing invoice' all convey the same information. A single well-formed sentence would carry the same signal with less noise.

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 of this complexity — deeply nested line_items with revenue_recognition, credit_notes, custom_fields, many enums, and no output schema — the description is far too thin. It omits the core semantics of partial update (unmentioned fields are preserved), any editing restrictions tied to invoice status, and the relationship to the full-update and line-item sibling tools. An agent must infer critical call constraints from an unwieldy nested schema.

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 67% and the schema documents most body fields (status, currency, line_items, etc.), so the schema carries most of the load. The tool description adds no parameter-level detail, and the required `id` parameter is undocumented in both the schema and the description. Some schema descriptions are auto-generated junk (e.g., 'Adds nested create feature' for the body, a ModelSerializer note for credit_notes), so 67% coverage overstates quality.

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 states a specific operation — 'partially updating an existing invoice' — with a clear resource (Invoices) and endpoint (PATCH /invoices/{id}/). The word 'partial' distinguishes it from the sibling wafeq_invoices_update, and the write semantics distinguish it from retrieve/destroy siblings. However, the same idea is stated three times ('updates data', 'Partial update invoice', 'Endpoint for partially updating an existing invoice') and no sibling is explicitly named.

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?

There is no guidance on when to use this tool versus wafeq_invoices_update (full update) or wafeq_invoices_line_items_partial_update. The description never explains that PATCH means only supplied fields change, nor that this tool should be preferred over the full update when modifying a subset of fields. An agent has no basis to choose between this and its update siblings.

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