Add and remove tags (20 max)

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

Annotations only declare readOnlyHint=false and openWorldHint=true; the description adds genuinely useful behavior the agent could not otherwise infer: the call is a no-op unless confirm:true is supplied, and there is no server-side dry run, so the preview is client-side only. It stops short of disclosing whether removals are irreversible, what happens when the 20-tag ceiling is exceeded, or whether permission scopes are required.

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?

Two compact sentences, front-loaded with the operation and immediately followed by the safety gate, with zero filler. Minor redundancy: '20 max' is duplicated from the title and could instead be used for a more informative detail.

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 mutating tool with a nested body and no output schema, the description covers the critical confirm/preview contract, which is the most important omission risk. However, it leaves out the tag-count boundary behavior, the failure semantics of remove, and any authorization notes, so an agent still lacks a full picture of consequences.

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 50%, and the schema already documents confirm, idempotencyKey, and the add-item character set, so the baseline is 3. The description's '20 max' restates the schema's maxItems=20 rather than adding meaning, and it says nothing about the id path parameter or the semantics of the remove array (e.g., whether removing a non-existent tag errors).

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 pair and resource (add/remove tags on a creative-library item) and anchors it to the PATCH /v1/creative-library/{id}/tags endpoint, so the agent can distinguish it from read-only siblings like creativeLibrary_get and creativeLibrary_list. It does not explicitly name a sibling alternative, but no sibling overlaps in function, so ambiguity is low.

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 when-to-use or when-not-to-use guidance beyond the confirm gate. Nothing tells the agent when to prefer this over creativeLibrary_upload, creativeLibrary_file, or creativeLibrary_remove, nor what prerequisites (permissions, existing tags) are needed. The 20-max limit is stated but not framed as a decision constraint.

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