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

Adds substantial context beyond the annotations: 'writes to Studio, creates billable AI usage', synchronous execution, 'Task support: forbidden', the validate_only/preview_only/execute mutation modes, and the completed_items_not_rolled_back partial-failure policy. It also documents the seat requirement for mutations and deterministic idempotency-key derivation. Not a 5 only because the response-handling boilerplate is orchestration guidance rather than tool behavior.

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?

Front-loads the purpose and the save/permission condition, then moves to operational constraints. The prose is dense but nearly every clause adds a distinct fact. Minor redundancy from the title/description duplication and the length of the response-formatting boilerplate against such thin parameter documentation keeps it out of 5.

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?

Behaviorally it is thorough for a complex mutation, and the editability of return values is covered by the presence of an output schema. However, for a 40-parameter tool with 3% coverage and no required fields, the description leaves nearly all parameter semantics undocumented, so an agent cannot assemble a valid call from the definition alone. The parameter documentation gap is the dominant deficiency.

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?

With 40 parameters and only 3% schema description coverage, the description must carry parameter meaning but covers at most seatId/seatName, idempotencyKey, creativeIds and the save flag. The remainder (brief, input, audience, campaign, template, marketContext, outputs, locale/market fields, etc.) is left entirely undocumented in schema and description, leaving an agent unable to supply most inputs correctly. It also references 'saveToStudio', a name that does not exist on the schema (the field is 'persistence' with value 'save_to_studio'). No parameter semantics 1-5 rules for 0 params apply here since there are 40.

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 ('Generate Studio-ready design briefs') plus scope ('for one or more creatives') and the inputs that shape it (campaign context, brand rules, audience, offer, format constraints). Critically, it labels itself a 'deprecated alias for create_creative_brief', which lets an agent distinguish it from the sibling without opening either schema.

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?

Explains the conditional save path: persistence happens only when creative IDs and a save flag are supplied and the caller holds Studio write permission, otherwise a non-destructive proposal is returned. It also flags deprecation, pointing the agent toward the canonical sibling. It does not, however, state an explicit 'prefer create_creative_brief' instruction or any when-not-to-use exclusion.

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