llm_redteam__run_probe_suite

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

Annotations already flag readOnlyHint=false and openWorldHint=true, but the description goes further: it discloses quota consumption per probe, that probes never request genuinely harmful content, and precisely how success is judged (target reproduces a random one-time token). That is meaningful behavioral context an agent cannot get from the annotations.

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 tight sentences: purpose first, authorization/cost constraint second, safety rationale third. Every sentence carries information and nothing is redundant.

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 non-idempotent, open-world tool with no output schema, the description covers authorization, cost, and success criteria. It stops short of describing the shape of results (per-probe pass/fail, reproduction evidence), which an agent would want, but the token criterion covers the essential outcome.

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 75% and the nested target union is fully documented inline, so the description needn't re-explain parameters. It loosely frames the target as an 'endpoint or chatbot you control' but adds no new semantics for probeIds, maxProbes, or categories beyond what the schema already states.

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 and resource ('Run canary-based red-team probes against a live LLM endpoint or chatbot') plus the exact technique classes tested (jailbreak/extraction/obfuscation bypass of guardrails). This is clearly distinguishable from the companion llm_redteam__list_probes, which only enumerates probe IDs.

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?

Provides a hard precondition ('ONLY point this at an endpoint you own or are explicitly authorized to test') and a cost warning ('every probe consumes API quota'), which tells the agent when NOT to call it. It lacks explicit routing guidance to alternatives (e.g., call list_probes first to choose probeIds), leaving that inference to the schema.

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