generate_brief

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

With no annotations, the description carries the full burden. It states the tool generates a brief (implying a read/create operation) and mentions that the executing agent can run fully from the output, which implies the output is complete. However, it does not disclose whether the tool writes to storage, requires authentication, has side effects, or what happens if required inputs are missing. It adds some context but leaves critical behavioral aspects undisclosed.

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 sentences, no filler. The purpose and key benefit (self-contained, no callback) are front-loaded. Every phrase earns its place, and the structure is clear and efficient.

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?

Given the tool's complexity (13 parameters, nested objects, no output schema), the description is incomplete. It lists the brief's contents but never describes the output format (text, JSON?), how required inputs are used, or any constraints. No edge cases or error conditions are mentioned. The description relies on the schema for required fields but those are not obvious to an agent without reading it; also the description offers no guidance on when to use this over adjacent tools like build_campaign.

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 only 15% (2 of 13 parameters have descriptions), so the tool description must compensate. The description mentions content like 'budget split' and 'posting windows' which maps loosely to parameters like total_budget and duration_weeks, but it does not explain how any of the parameters should be set, their formats, or their interdependencies. It offers high-level hints but insufficient detail for an agent to correctly fill all 13 parameters, especially since several lack schema descriptions.

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 clear verb ('Generate'), resource ('campaign brief'), and content list ('positioning, budget split, posting windows, resolved BrandTokens, and execution contract'). It distinguishes itself from execution tools by calling it a 'handoff artifact' and noting that the executing agent can run 'without calling back.' However, it does not explicitly name alternative sibling tools, relying on implicit contrast.

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?

The phrase 'for any brand execution agent' gives some context that this is used to hand off to another agent, and the statement 'The agent can execute without calling back' implies you use it when you need a self-contained task spec. But it provides no explicit 'when not to use', no comparison to alternatives like build_campaign, and no mention of prerequisites. Usage guidance is inferred rather than explicit.

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