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

Well beyond what the annotations declare, it discloses the exact return payload (per-scene signed quotes, one server-calculated total, approval_handle, approval_url) and, critically, what does NOT happen here (no provider job starts, no wallet debit). It also discloses the human-approval requirement and the two accepted confirmation channels, which is the key behavioral fact an agent could otherwise get wrong.

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 sentences, front-loaded with the use case, then the return shape and non-effects, then the hard constraint and approval requirement. Every clause carries an operational fact; no filler and no restatement of the tool name.

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 batch tool with a deep nested schema and no output schema, the description covers purpose, what is returned, side-effect scope, ordering constraint, and the approval gate — enough to call it correctly. Remaining gaps are minor but real: it does not say how scene_id values are sourced, whether quotes expire, or how quoting failures surface per-scene versus batch-wide.

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?

Top-level schema coverage is 0%, so the description carries the burden of explaining the single `scenes` array; it does constrain the array (1–10 entries, independent scenes, existing input media) and its 'reference is the future output of a scene in the same batch' rule effectively encodes when a result_origins dependency is illegal. It does not explain scene_id, family selection, or where values come from (the schema's nested note points at aimixer_options), so some per-field meaning is still only in the schema, but the description adds real constraint semantics rather than restating types.

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 verb and resource (returns signed quotes for a batch of 1–10 independent MixerAI scenes) and bounds it explicitly at both ends (min 1, max 10). It implicitly but clearly distinguishes itself from the single-scene sibling aimixer_quote by the word INDEPENDENT and by naming aimixer_batch_submit as the downstream step, so an agent can route between them without opening schemas.

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 gives an explicit precondition (input media must already exist), an explicit exclusion (never batch a video whose reference is the future output of a scene in the same batch), an explicit follow-up tool (aimixer_batch_submit), and the gate that must be satisfied before that follow-up. Nothing about when to use or when not to use it is left to inference.

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