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

Annotations already cover read-only/idempotent/destructive, and the description reinforces this with 'Reading a recipe does not touch the scene.' More valuable is the added context about content and limits: bb_ helper examples, result checks, and the caveat that numbers are starting points not quality guarantees, which shapes how the agent should treat returned data.

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?

Dense but mostly earning its space: capabilities, available values, invocation modes, and caveats are all front-loaded. Minor redundancy between 'does not touch the scene' and the readOnlyHint annotation, and the recipe list could be more scannable, but nothing is wasteful.

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?

With no output schema, the description carries the burden of explaining returns and does so adequately: listing mode returns names with descriptions, and recipes contain bb_ helper examples and result checks. Combined with full schema coverage and rich annotations, an agent has enough to call this correctly.

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 coverage is 100%, so the baseline is 3, but the description goes further by enumerating the accepted recipe identifiers and explaining the omit-to-list behavior, effectively supplying the valid value set the schema lacks (0 enums). It adds real meaning about how to use or skip the single optional parameter.

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 and resource ('Read a relevant recipe', 'get_blender_recipe') and enumerates the five packaged workflows (ad-clip, interior-scene, match-photo, product-shot, stylized-character), so an agent knows exactly what it retrieves. It is distinguishable from siblings like search_blender_manual or lookup_blender_api, though the opening phrase 'Optional task workflows' is a slightly soft framing before the concrete list.

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?

Gives a clear usage condition ('Read a relevant recipe when it helps the task') and an explicit no-argument mode ('call without a name to list them with descriptions'). It does not name competing siblings such as search_blender_manual or lookup_blender_api, so the agent must infer which reference source to prefer.

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