draft_brief

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains that the tool returns a plan with specific components, and it adds important behavioral rules: every claim must trace to a fact, invented details must not be attributed to sources, and thin sourcing should be marked as background. It does not mention side effects or state changes, but for a drafting/generation tool this is reasonably transparent.

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?

The description is longer than average but front-loaded with the tool's role and output, followed by essential procedural rules. The imperative instructions are relevant and not filler. A small deduction for slightly repetitive emphasis like 'ACT ON IT IMMEDIATELY' and 'You are the writer' which could be condensed without losing meaning.

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 absence of an output schema and annotations, the description does a solid job of explaining what the plan contains continued and how the result should be used ('pass it to build_schema as `article`'). It also covers the downstream quality checks. It is not a 5 because it omits any clarification about the relationship of all input parameters to the returned plan, and the boundary between what draft_brief returns and what the agent writes is slightly ambiguous.

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 0%, so the description must compensate for five parameters. It mentions 'facts' and 'keywords' and indirectly references 'FAQ questions', but it does not explain the meaning or expected format of 'headline', 'references', or 'faq_candidates'. The parameter names are self-explanatory to a degree, but the description does not provide enough semantic detail to fully compensate for the total absence of 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 specific purpose: 'Takes the verified facts and the keywords and returns the plan' and enumerates the plan contents. It also ties the tool to a concrete pipeline position ('Step 5') and names downstream tools like build_schema, which helps distinguish it from siblings. It is slightly less than a 5 because the opening mixes tool purpose with an instruction to 'write the article,' blurring whether draft_brief itself produces the plan or the full article.

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 description gives clear usage context: it is Step 5, and it explicitly instructs the agent to act immediately, not to print the brief for the user, and to run find_ai_words and review_draft before build_schema. This effectively explains when and how to proceed. It does not explicitly name an alternative tool to use instead, but the pipeline ordering provides sufficient guidance.

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