Screen untrusted text for prompt injection, relevance, and substance before AI context use. Provides a decision signal without executing or fetching content, enabling safe gating and classification.
Screen supplied external text for prompt injection, relevance and substance. Never executes or fetches the text.
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | ||
| purpose | No | ||
| block_at | No | ||
| review_at | No |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already establish readOnlyHint and idempotentHint, and the description adds a valuable safety boundary: 'Never executes or fetches the text.' This tells the agent the tool analyzes the supplied text without making network calls or running content, which is behavior beyond what the annotations alone state.
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?
Two short sentences deliver the core purpose and a critical negative guarantee with no filler. The key verb and object appear first, making the definition easy to process quickly.
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?
The tool has four parametersasia and no output schema, and the description leaves purpose, block_at, and review_at undefined while also not explaining the result format of the screening. The definition is enough to call the tool with just text, but not enough for an agent to use the optional controls or interpret the response confidently.
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, but it only references 'text' and leaves purpose, block_at, and review_at entirely unexplained. It adds the useful idea that text is external/unsafe, but an agent cannot determine how the optional parameters affect screening behavior.
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 uses the specific verb 'Screen' against 'supplied external text' and names the screening criteria: prompt injection, relevance, and substance. This clearly states the tool's function, though it does not explicitly distinguish it from sibling tools such as system_one_review, system_one_verify, or system_one_classify.
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 implies a use case ('screen supplied external text') but gives no guidance on when to prefer this tool over the many siblings, nor any conditions or exclusions. An agent is left to infer when system_one_screen should be called rather than system_one_review, system_one_gate, or system_one_verify.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.