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

Annotations already declare the write, idempotent, and non-destructive profile, so the bar is lower. The description adds genuine context beyond them: favorites are per-user scoped (not workspace-wide) and the operation consumes no credits, which affects whether an agent should worry about cost. What is missing is whether unfavoriting is reversible/persistent or any per-user auth implication.

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 short sentences, front-loaded with the action, then scope, then cost. Nothing is redundant and each sentence contributes distinct information.

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 an output schema present, return values needn't be explained, and annotations plus 100% parameter coverage carry the rest. The only soft spot is the absence of guidance on the per-user/permission implications of favoriting on someone else's behalf, which is minor for a low-risk toggle.

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 100%, so creativeId, brandId, and favorite are already fully documented with sourcing hints. The description's 'or unmark it' reinforces the boolean semantics but adds no sourcing or format detail beyond the schema, so the baseline 3 applies.

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 ('Mark a creative as one of the user's favorites, or unmark it') and clarifies the set/unset duality that the name alone doesn't convey. It implicitly separates itself from sibling mutators like tag_creative or rename_creative by naming the Favorites concept, though it never explicitly contrasts with those siblings.

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?

'Favorites are per person and show in the Library's Favorites view' implies when to use it (curating a personal shortlist visible in that view) and 'Free' signals no credit cost. There are no explicit when-not conditions or named alternatives such as tag_creative for organizational categorization, so usage is inferred rather than directed.

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