detect_tool_poisoning

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

With no annotations, the description should fully disclose behavior. It mentions the analysis scope (OWASP vectors) but does not state that the tool is read-only, safe, or non-destructive. It also lacks details on potential side effects or rate limits.

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, concise and front-loaded with the core purpose. Every sentence is meaningful, and there is no redundant information.

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 description lacks any mention of the return value or output format, which is critical for a security analysis tool. Users and AI agents need to know what the result looks like (e.g., risk score, list of indicators). Additionally, no output schema is provided, and annotations are absent.

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?

The single parameter 'tool_definition' is fully described in the schema (100% coverage), but the description adds value by explaining that the tool analyzes the description text for hidden instructions and covers specific attack vectors, going beyond the schema's generic description.

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 analyzes MCP tool definitions for poisoning indicators, specifically hidden instructions in descriptions that manipulate agent behavior, covering OWASP Agentic Top 10 attack vectors. It is specific and distinguishes from siblings like detect_prompt_injection.

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 usage when analyzing tool definitions for poisoning, but it does not provide explicit guidance on when to use this tool versus alternatives like detect_prompt_injection or validate_scope_contract. No when-not-to-use or prerequisites are stated.

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