Add Visual

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

Annotations are sparse (only `openWorldHint: false`), so the description carries the burden of behavioral disclosure. It mentions batch addition and inline formatting but does not explain key behaviors such as whether visuals are appended or replaced, idempotency, permissions, or error handling. The potential for destructive actions is not addressed.

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 very concise: four sentences with no wasted words. The first sentence front-loads the core action, followed by key features and specific examples. Every sentence adds value.

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 and the lack of an output schema, the description is adequate but incomplete. It covers main use cases but omits return value information (e.g., what IDs are returned) and behavioral details like duplicate handling or error conditions. The tool has many adjacent siblings, but the description does not fully differentiate them.

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 coverage is 80%, so the schema already documents most parameters. The description adds value by explaining visual-type-specific bucket names (Series, Category) and directing users to `pbir_lookup_theme_property` for valid names. This semantic enrichment goes beyond the schema.

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 clearly states the tool adds visuals to a page in batch via the `visuals` array. It distinguishes from sibling tools like `pbir_format_visual` by noting that inline formatting avoids extra calls. Specific visual types (stacked charts, KPI card, scatter) are mentioned, making the purpose precise.

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 provides guidance on when to use this tool (batch add with inline formatting to avoid extra calls) and gives specific usage tips for different visual types (e.g., 'Stacked charts need a Series binding'). It also recommends using `pbir_lookup_theme_property` for valid names. However, it does not explicitly exclude alternatives or state when not to use it.

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