scan_agent_prompt

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

No annotations are provided, so the description carries the full burden. It states the tool scans and returns a result but does not disclose whether it modifies any state, requires specific permissions, or has side effects. For a security tool, behavioral traits like read-only nature, network calls, or audit logging should be mentioned.

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 two sentences long with no wasted words. It front-loads the purpose and then gives actionable verbosity guidance. Every sentence earns its place.

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 no output schema, the description mentions possible return values (BLOCK/WARN/LOG/ALLOW), which is helpful. However, it does not specify whether the result is a simple string or a structured object. It also doesn't cover potential errors or timeouts. For a simple tool, the basics are covered, but more details on output format would improve completeness.

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. The description adds minimal value beyond the schema: it explains verbosity values ('minimal' for action only, etc.), which are already in the enum. The description doesn't clarify the 'context' object beyond the schema. Overall, the description does not significantly improve parameter understanding.

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 tool scans a prompt for malicious intent and returns a classification (BLOCK/WARN/LOG/ALLOW). It specifies the resource (prompt) and action (scan), which is specific enough to differentiate from sibling tools like 'scan_agent_action' or 'scan_security', though it could be more explicit about what constitutes 'malicious intent'.

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 provides guidance on the verbosity parameter (minimal/compact/full) but fails to mention when to use this tool versus alternatives. With siblings like 'scan_agent_action' and 'scan_mcp_server', the description should indicate scenarios where prompt scanning is appropriate and when other tools are preferred. No 'when not to use' or alternatives are mentioned.

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