llm_redteam__run_probe_suite

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

Adds meaningful context beyond the annotations: every probe consumes API quota on the target, probes never request genuinely harmful content, and success is measured by reproduction of a random one-time token. The annotations declare openWorldHint/readOnlyHint=false, but the description supplies the cost and mechanism detail those hints cannot.

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?

Three sentences, front-loaded with the action, followed by the safety constraint and then the mechanism. Every sentence carries distinct value with no redundancy.

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?

For a tool with a complex nested target config and no output schema, the description covers what is being tested and how success is judged (canary token). It omits the shape of the returned findings, but the safety, cost, and success-criterion context make it largely complete.

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 75%, with the target oneOf variants and probeIds/maxProbes/categories all documented in-schema. The description adds no parameter-level detail (e.g., how probeIds and categories interact or what maxProbes defaults to), so the baseline 3 applies.

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?

States a specific verb (run) and resource (canary-based red-team probes) against a named target type (live LLM endpoint or chatbot). An agent can distinguish this from the sibling llm_redteam__list_probes without opening either schema, since it clearly describes active probing rather than enumeration.

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?

Gives strong context: test whether jailbreak/extraction/obfuscation techniques bypass guardrails, with an explicit authorization boundary ('ONLY point this at an endpoint you own or are explicitly authorized to test'). It does not explicitly name list_probes as the discovery alternative, but the when-to-use condition is unambiguous.

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