pbi_define_brief

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

The description clearly discloses that the tool writes a file (`pbi-brief.json`) next to the .pbip, outside .Report/.SemanticModel, and that overwriting is normal because dashboards change purpose. It also explains that the agent must not fabricate answers. This adds meaningful behavioral context beyond the sparse annotations and does not contradict them.

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 long but purposeful. It front-loads the main verb and resource, uses a bolded warning for the most important behavioral rule, and packs useful details about parameter semantics and file storage. While not as terse as possible, every sentence adds relevant context.

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 tool that writes a brief file, the description is fairly complete: it explains the file location, why it is stored there, the human-interaction requirement, and key parameters like delivery and critical_fields. The presence of an output schema reduces the need to describe return values. Some parameter descriptions are missing, but the overall context is sufficient for effective use.

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?

The input schema has 0% description coverage, so the description carries a heavy burden. It does explain `delivery` (with enum values and meaning) and `critical_fields` (structure and purpose), and indirectly covers `purpose` and `audience`. However, several other parameters like `decisions`, `non_goals`, `request_id`, `key_questions`, and `update_cadence` are not described, leaving gaps.

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 opens with a specific verb and resource: 'Escribe el BRIEF DE INTENCION del tablero' (Write the intent brief of the dashboard). It clearly defines the artifact's role as governing other pieces and distinguishes it from sibling tools like pbi_get_brief by focusing on creation and intent capture rather than retrieval.

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 strong usage guidance: it explicitly says to ask the human before calling, lists specific questions to ask, and warns that an agent-invented brief is worse than none. It does not explicitly name alternative tools, but effectively communicates when not to use it by emphasizing that answers must come from the human.

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