add_advanced_filter

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 the structure of conditions, combine operator, fieldKind, and valueType, which adds useful context beyond the schema. However, it does not disclose side effects (e.g., whether existing filters are replaced, whether the filter is immediately applied, or any validation behavior for invalid inputs). This is typical for a mutation tool but could be more 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 a single, dense sentence that front-loads the core purpose and then efficiently lists the key parameter semantics. Every clause adds value, with no redundant or filler content. It avoids repeating schema information and focuses on the most actionable guidance.

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 with 10 parameters and a nested JSON structure, the description covers the essential usage: the condition format, allowed operators, combine logic, fieldKind, valueType, and scope-specific parameter requirements. It leaves a couple of minor gaps (e.g., what to pass for report scope, behavior when more than two conditions are provided) but is largely complete given the schema's rich parameter descriptions. The lack of an output schema means return behavior is not addressed, but the core usage is well documented.

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 high (90%), but the description adds significant meaning beyond the schema: it enumerates the allowed operators (gt|gte|lt|lte|eq|ne|isblank|isnotblank|contains|startswith), clarifies the combine option (and|or), and explains the scope-to-parameter mapping (visual requires page+visual, page requires page). This helps the agent construct valid JSON conditions and correctly choose parameters, exceeding what the schema alone provides.

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's function: adding an ADVANCED multi-condition filter with And/Or logic at visual, page, or report scope. It specifies the key differentiator (up to two conditions on the same field joined by And or Or) and explicitly distinguishes it from basic filters, making it easy to differentiate from sibling filter tools like add_visual_filter.

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 concrete usage context, including the scope options and the requirement to pass page+visual for visual scope and page for page scope. It does not explicitly name alternative tools or exclusions, but the 'ADVANCED' label and condition details imply when this tool is appropriate compared to simpler filter tools. Minor gap: no explicit 'use this instead of X' guidance.

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