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

Annotations already declare read-only, idempotent, closed-world, non-destructive, and the description still adds substantive behavior: what is analyzed (4 categories, 200+ patterns), what comes back (boolean verdict, 0-1 confidence, matched patterns with evidence, decoded payloads), and the performance envelope (<100ms p95). That is real added context rather than restatement.

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?

Five tight sentences, front-loaded with purpose then capability then usage then return contract. Most sentences earn their place, though "200+ detection patterns" leans toward marketing filler and the latency claim could be trimmed for a definition this short.

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's return-value sentence is load-bearing and present, which is exactly right. Remaining gap is guidance on interpreting output — e.g., what a middling confidence score or a match should trigger — plus any error behavior.

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 `prompt` and `context` semantics are already fully documented — including the enum tolerance levels — in the schema itself. The description adds nothing parameter-specific, so baseline 3 applies.

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+resource ('Detect prompt injection in text') and immediately scopes it with four named detection categories and a pattern count. The resource domain is unmistakably distinct from siblings like check_domain, check_ip, and check_password, so no cross-reading is needed.

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?

"Designed for real-time inline usage before processing untrusted user input" gives a clear, actionable when-to-use trigger plus a latency budget that justifies inline placement. It stops short of naming alternatives (e.g., scan_skill for skill definitions, full_scan for broad sweeps) or stating when not to call it.

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