rt_check_tool_poisoning

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

No annotations are provided, so the description carries full burden. It mentions returning findings with pattern and severity but omits details like performance impact (analyzing ALL tools), side effects, or resource usage. It conveys a read-only operation but lacks depth.

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 three concise sentences: purpose, patterns checked, output summary. No redundancy, front-loaded information. Every sentence earns its place.

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 no output schema, the description sufficiently indicates return format ('findings with matched pattern and severity'). It lacks explicit structure but is adequate for tool selection. Could be improved with more detail on output fields.

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 100% (7 parameters fully described in schema). The tool description adds no additional meaning to parameters; it doesn't mention any parameter. Baseline 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 clearly states the tool's purpose: 'Analyze ALL tool descriptions for hidden prompt injection instructions.' It lists specific patterns checked (file read, exfiltration, etc.), which distinguishes it from sibling security tools like rt_check_prompt_injection and rt_check_instructions.

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 when to use by listing the types of injection checked (e.g., file read, exfiltration). It does not explicitly state when not to use or alternatives, but the context of sibling tools makes it clear this is for tool-poisoning detection.

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