screen_content

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

With no annotations, the description carries the full burden of behavioral disclosure. It clearly states the outputs and the routing rules (low confidence → review, severe → block), which is valuable. However, it does not mention potential side effects (e.g., data persistence, rate limits) or any prerequisites like authentication. For a classification tool, this is a minor omission, but the transparency is strong overall.

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 two sentences, with the core purpose front-loaded in the first sentence and decision logic in the second. There is no wasted language; every clause contributes to understanding the tool's behavior. It is optimally concise.

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 (multiple outputs, routing logic) and the absence of an output schema, the description provides a comprehensive overview of what is returned and the action logic. It does not detail the exact output format (e.g., JSON structure) or severity scale, but those may be inferable or dynamic. For an agent to call the tool correctly, the description is sufficient and complete enough.

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 100%, so both 'text' and 'categories' are already documented. The description does not add any new meaning beyond the schema; it only refers to 'text' implicitly and does not elaborate on 'categories'. Since the schema already does the heavy lifting, a baseline of 3 is appropriate.

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 verb ('screen'), a specific resource ('text'), and clearly enumerates the outputs (spam/toxicity probabilities, category, severity, confidence, action). It also conveys the decision logic (review vs block), making its purpose unambiguous. While it does not explicitly contrast with the sibling review_patch, the name and description make it distinct enough.

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 explains what the tool does but provides no explicit guidance on when to use it versus the sibling review_patch, nor any conditions for when it should not be used. The intended context (content moderation) is implicit, but an agent would have to infer when this tool is the right choice relative to alternatives.

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