prompt_injection_checklist

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and a closed-world scope, so safety is covered. The description adds genuine value beyond them by disclosing the output's nature: a partially-filled checklist template, not an automated scan — which sets correct expectations for the agent consuming the result.

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?

A single compact sentence, front-loaded with the action and scope, with the disambiguating 'not a scan' clause placed at the end where it is still visible. Nothing is padded, though the dense phrasing packs several ideas into one clause chain.

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?

An output schema exists, so return values needn't be explained, and the safety profile is in annotations. But with four required, undocumented parameters (including a structured tools array and a fixed enum of untrusted source types), the description leaves the agent to infer input shapes it should really be told.

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 0% across four required parameters, so the description must carry the burden. It only gestures at two of them conceptually ('tools and untrusted data sources') and says nothing about the agent name, humanInLoop, or the critical per-tool 'mutating'/'external' flags that drive the checklist's contents.

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 (enumerate) and resource (injection paths and controls) scoped to an agent's tools and untrusted data sources, and the trailing clause clarifies the artifact is a checklist rather than a scanner. It doesn't name the adjacent sibling threat_model, so differentiation is only partial, but the purpose itself is unambiguous.

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 phrase 'produces a checklist with status to fill, not a scan' implicitly tells the agent when NOT to reach for this (i.e., when an automated scan is wanted), which is useful. However, no alternative tool is named and no prerequisites or context for when this belongs in a workflow (e.g., pre-deployment review vs. threat_model) are given.

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