driftguard_prompt_shield

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

No annotations are supplied, so the description carries the full burden. It says the tool will 'rilevare e bloccare' attacks but never explains what 'bloccare' means operationally — whether the call aborts, returns a verdict, or merely reports a finding. It also advertises scanning of 'file o issue esterne' while the schema accepts only a free-text string, leaving the actual capability ambiguous.

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?

One front-loaded sentence that opens with the verb and enumerates the threat categories without filler. It only loses a point because the file/issue enumeration introduces an input claim the schema does not support, which is noise 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?

With no annotations and no output schema, the definition must explain the result shape, and it does not: an agent cannot tell whether the return is a boolean verdict, a risk score, or a list of findings. The ambiguity around 'bloccare' and the overlap with driftguard_scan_secrets are left unresolved, which is a real gap for a security-gate tool.

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% for the single required parameter, so the baseline of 3 applies; the description adds nothing about the shape, limits, or size of the text to pass. It slightly muddies parameter meaning by implying file and issue inputs that the one string parameter cannot express.

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 names a specific verb and a precise class of target ('Scansiona testi, file o issue esterne') plus the exact threats detected: prompt injection, jailbreak, credential theft. That is far more than a restatement of the name. It stops short of a 5 because it never differentiates itself from the sibling driftguard_scan_secrets, which overlaps squarely on 'furto di credenziali'.

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?

Usage is only implied: the schema hint 'Il testo da esaminare prima di elaborarlo' suggests a pre-processing gate, but the description itself gives no when-to-use statement. There is no exclusion and no pointer to alternatives, so an agent facing both this tool and driftguard_scan_secrets has to guess which one handles leaked credentials.

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