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

Annotations provide readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false. The description adds that it 'Adds or updates' (mutation) and returns the item ID and quoted price. It also mentions bulk support. However, it doesn't disclose details like whether it requires an open order (it says 'on an open order' but doesn't explain what happens if the order is not open), or any side effects beyond the upsert. With annotations already indicating non-read-only and non-destructive, the description adds some context but not rich behavioral detail.

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 concise: two sentences. The first sentence states the purpose and return value. The second sentence mentions bulk support. It's front-loaded and efficient. However, it could be slightly more structured (e.g., separating the bulk support note), but overall it's appropriately sized.

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?

Given the complexity of the input schema (nested objects, three item variants, multiple required fields), the description is insufficient. It doesn't explain the different item types (e.g., single media vs. multiple media vs. verbatim), the meaning of fields like 'include_captions' or 'cue_options', or how to use 'item_id' for updates. The output schema is absent, so the description should clarify return values more, but it only mentions 'item ID and quoted price.' The bulk support is mentioned but not detailed (e.g., how order_ids interacts with order_id).

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 must compensate. The description mentions 'order_ids' for bulk support, but doesn't explain the 'request' object structure, the 'item' variants, or the 'account' parameter. The schema is complex with nested objects and three item variants, but the description provides no guidance on how to construct the request. This is a significant gap.

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 clearly states the tool's purpose: 'Upsert Order Item. Adds or updates an order item on an open order.' It specifies the verb (upsert/add/update), the resource (order item), and the context (on an open order). It also mentions the return value (item ID and quoted price). However, it doesn't explicitly distinguish from sibling tools like elevenlabs_public_remove_order_item or elevenlabs_public_update_order, though the name and description make the distinction fairly obvious.

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 implies usage: it's for adding or updating items on an open order. It mentions 'Bulk support: accepts order_ids for batched execution,' which is a usage hint. However, it doesn't explicitly state when to use this vs. alternatives (e.g., when to use update_order instead, or when an order is not open). The context is clear but exclusions or alternatives are not explicitly stated.

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