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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds the HTTP endpoint and the threat categories, but says nothing about what a detection result looks like, thresholds tied to sensitivity, or latency/rate limits.

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?

Two tight sentences, front-loaded with the core purpose and followed by concrete attack categories and the endpoint. No filler, though the parenthetical endpoint adds limited value for an agent invoking the tool.

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 output schema, the description should explain the shape of a detection verdict (flagged/not flagged, category, confidence), and it does not. Safety behavior is covered by annotations, but the return contract remains a real gap for a detection API.

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 baseline is 3; the description contributes no param-specific meaning. The schema's own examples for `context` and `sensitivity` are thin, but that is a schema problem rather than a description one.

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 and resource: catches prompt injections, role hijacks, and encoded jailbreaks in user inputs and RAG chunks. That scope hint helps separate it from sibling guards (llm_output_guard, agent_code_guard, command_sql_guard), but no sibling is named explicitly.

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?

Frames the use case (scanning untrusted user input and RAG chunks before they reach a model) but gives no explicit when-to-use vs when-not guidance, and never points to an alternative sibling for outputs, agent code, or SQL.

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