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

Annotations already cover mutation/destructive intent, but the description adds valuable behavioral detail: on a match it returns NO_COMMIT with `reason` and `findings` naming the matched categories. It also discloses the cost point ($0.02) and the fact that it is a pre-action gate. No contradiction with annotations exists, though it does not explicitly state the non-match return path.

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 dense but each clause adds functional value: the pre-action positioning, the category/examples, the return behavior, and the pipeline ordering. It could be slightly tightened, but it avoids fluff and front-loads the most important identification ('Crypto Jailbreak & Injection Detection') and operational context.

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 complex classifier with an output schema, the description covers what patterns are detected, what a match returns, and how it fits into the pipeline. It could be more explicit about how this differs from the generic dcl_evaluate_jailbreak sibling, but it names the relevant adjacent checks and gives enough context for correct invocation.

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 100%, so the schema already explains both `response` and `agent_id`. The tool description adds no new parameter-level detail beyond restating that `response` is the input to screen. The baseline of 3 is appropriate; the description does not harm but also does not carry additional parameter semantics.

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 identifies this as a specialized crypto jailbreak/injection detection screen, with a specific verb ('Detect'/'screens') and explicit resource (input prompts in the crypto pipeline). It differentiates itself from generic jailbreak detection by naming crypto-specific injection categories and examples, so an agent can distinguish it from siblings like dcl_evaluate_jailbreak, dcl_evaluate_wallet, and dcl_evaluate_mev.

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 gives explicit placement: 'run this FIRST in the DCL crypto pipeline, before wallet/trade/MEV checks.' It also explains why, noting this tool 'screens the input itself rather than a decision built on top of it.' This is concrete, actionable guidance that tells the agent when to use it relative to sibling tools.

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