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

Discloses behavior well beyond the annotations: create is born as a private draft with title required; remove detaches the piece without touching the piece itself; note without a note erases it; add on an already-present piece swaps the note; reorder places uncited refIds after the cited ones in their old order; scope is limited to the caller's own account and pieces; and it is free. That is exactly the side-effect detail an agent needs before mutating user 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?

One dense paragraph carrying eight sub-actions, an itemType taxonomy, a naming convention and scope rules — front-loaded correctly with the purpose, but never broken into structure, making it hard to scan for the action the agent actually needs. Nearly every sentence earns its place, but the lack of formatting costs it.

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 an eight-parameter, eight-action mutation tool with no output schema, the description covers each action's semantics, required fields, side effects and account scoping, and hints at the shape of get (pieces in order with notes) and list. Return shapes for the other actions are left implicit, which is the only material gap.

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 88%, so the schema already carries most parameter meaning. The description restates rather than extends it: the itemType list, the id-or-slug lookup for `collection`, and the 'escolhida'/'tentativa' note convention all appear in the field descriptions too. The one thing it adds is which sibling tool yields which id per itemType, but that is thin value over an already well-documented schema.

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 concrete verb+resource: Collections are the album of any piece (image, video, design system, character, etc.) within the user's account, and enumerates the eight sub-actions explicitly. The relation to siblings is only indirect — it names sapiens_image, sapiens_video and sapiens_gallery as sources of ids and rules out publishing/cover-setting (sapiens_publicar territory) — but it never contrasts itself head-on with another collection-ish tool.

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 real usage context: it is the place for the CHOSEN piece among a project's attempts, with the 'escolhida'/'tentativa' note convention and the reorder-to-top recipe. It also draws an explicit boundary — publishing the Collection and picking a cover are the owner's gestures in the Acervo, never the agent's. It stops short of saying when to use which sibling for listing pieces versus Collections.

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