run_target_tool

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

The description adds value by disclosing the approval requirement for non-read-only tools, complementing the annotations (readOnlyHint=false, destructiveHint=true). It does not contradict the annotations and provides behavioral context about the execution guard.

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, well-structured sentence that immediately communicates the action and the critical approval condition. It is concise without unnecessary elaboration, earning a top score.

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 presence of an output schema and thorough input schema, the description covers the essential safety aspect. However, it lacks broader context about the tool's role in the workflow (e.g., registering targets first) and potential failure modes, making it minimally complete but not rich.

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 input schema already covers all parameters (100% coverage), including target_id, tool_name, arguments, and allow_side_effects. The description does not add parameter-specific semantics beyond what the schema provides, so baseline score 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 'Execute one call' clearly states the core action of running a single target tool invocation. It effectively distinguishes this as the execution step among sibling tools like inspect_target and run_static_checks, though it could more explicitly mention the target tool context.

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 an explicit rule: non-read-only tools require explicit side-effect approval. This gives conditional guidance on when to set allow_side_effects, but it does not describe when to use this tool versus siblings or mention workflow dependencies like registering a target first.

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