Check text for prompt-injection patterns. A first filter, not a safety guarantee.
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"text": "<text>"
},
"name": "guard_check"
}
}| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds one genuinely useful behavioral caveat — that false negatives are expected and this must not be treated as a guarantee — but says nothing about what a check returns (boolean, category, confidence) or how to act on a positive result.
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 short sentences, front-loaded with purpose and immediately followed by the key limitation; nothing is wasted. The extreme brevity is close to under-specification, which is penalized elsewhere rather than here.
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 one-parameter, read-only filter with no output schema, purpose plus the reliability caveat covers most of what an agent needs. The remaining gaps — return shape and over-length handling — are small but real.
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?
Only one parameter exists and schema description coverage is 0%, but the description makes clear the sole input is the untrusted text to be screened. It does not mention the 4000-character cap or what happens with longer input, which is the one parameter detail an agent would need.
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?
"Check text for prompt-injection patterns" gives a specific verb (check) and a specific target (prompt-injection patterns), so an agent knows exactly what the tool screens for. Sibling names (arena_config, get_sentinel, list_sentinels, recent_attempts) suggest no competing scanner, but the description never states that itself, keeping it below a 5.
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?
"A first filter, not a safety guarantee" implies the intended usage position (an early, pre-LLM screen) but is stated as a caveat rather than guidance. There is no explicit when-to-use, when-not-to-use, or named alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.