Check Causal Influence Provenance for Injection Patterns

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds real behavioral context: what the check does, that it can run automatically under hosted governance, that content is optional so an entry may assert trust with nothing to scan, and why the risk applies to any trusted-context consumer. This goes well beyond 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?

A single dense paragraph, but it is front-loaded with the purpose before the generalization, parameter detail, and invocation timing. Every clause carries information; the only minor cost is run-on length rather than waste.

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 single-parameter tool with annotations covering safety and no output schema, the description supplies everything needed: what it scans, the entry shape, when to call it, and the automatic governance path. Nothing material is missing 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 coverage is 100%, so baseline is 3, but the description adds meaning: it explains the required 'kind' and 'trust' fields, enumerates their values, and clarifies that 'content' is optional with the rationale (an entry may carry only a trust assertion). That added interpretation exceeds the raw 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?

States a specific verb ('Scan') and resource (a list of upstream sources that causally shaped a proposed action) and names the outcome ('flag whether any of them are untrusted'). It explicitly positions itself against sibling rai_memory_write_check by generalizing beyond persistent memory, so an agent can distinguish it without opening the schema.

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 a clear trigger: 'Call this before letting a matched/untrusted source influence a real action.' It also notes the alternative execution path (automatic check under governance when arguments carry a '_provenance' key). There is no explicit when-not-to-use guidance, keeping it just below full marks.

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