harden_system_prompt

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

With no annotations provided, the description carries full burden. It mentions 'harden' which implies a write/mutation operation, but doesn't disclose critical behavioral traits like whether this is destructive, what permissions are required, rate limits, or what 'hardening' entails. The description adds minimal context beyond the basic action.

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 appropriately sized and front-loaded with the core purpose. The Args and Returns sections are clearly structured. While efficient, the formatting with markdown-style headers could be slightly more polished for maximum clarity.

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 complexity (mutation tool with nested objects, no annotations, no output schema), the description provides good parameter semantics but lacks behavioral context about the hardening process itself. It doesn't explain what 'hardened' means, what changes are made, or what the return dictionary contains. For a mutation tool with no structured safety information, this leaves significant gaps.

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?

With 0% schema description coverage, the description fully compensates by providing detailed semantic information for both parameters. It specifies the exact format and content requirements for 'redteam_results_summary' (top 20 categories, dictionary structure, success percent focus) and clarifies that 'system_prompt' should come from a specific tool. This adds significant value beyond the bare schema.

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 action ('Harden') and the resource ('system prompt'), and specifies the inputs needed. It distinguishes from siblings by focusing on prompt hardening rather than retrieval or management tasks. However, it doesn't explicitly contrast with tools like 'mitigation_guardrails_policy' which might have overlapping security purposes.

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 by specifying that inputs should be retrieved from specific sibling tools ('get_redteam_task_results_summary' and 'get_redteam_task_details'), which provides context for when to use this tool. However, it doesn't explicitly state when NOT to use it or name alternatives for similar hardening tasks, leaving some ambiguity.

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