prompt_guardScores prompt-injection / jailbreak risk for LLM inputs. Agent builders use this to sanitize user inputs before hitting their LLM. [price: $0.01/call USDC via x402]
| Name | Required | Description | Default |
|---|---|---|---|
| text | Yes | Input text |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It adds useful context such as pricing and the guard-oriented use case, but it does not disclose the return format, score interpretation, or whether high risk is indicated by a threshold. This is a meaningful gap for an agent deciding how to act on the output.
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 sentences with no filler. The core purpose is front-loaded, the use case is stated, and the pricing note adds actionable operational information without bloating the description.
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 single-parameter, no-output-schema guard tool, the description covers what it does, when to use it, and the cost. The main missing piece is the nature of the returned score, but overall it is adequately complete for the tool's simplicity.
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% with a clear 'Input text' description, so the baseline is 3. The description adds slight extra meaning by framing the text as 'LLM inputs' in the context of prompt-injection risk, but it does not go beyond that.
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 uses a specific verb ('Scores') and resource ('prompt-injection / jailbreak risk for LLM inputs'), making the tool's function immediately clear. It also distinguishes itself from related guards like pii_guard and json_guard by focusing specifically on injection/jailbreak risk.
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?
Explicitly identifies the target use case: agent builders sanitizing user inputs before calling an LLM. It does not state when not to use it or name alternatives, but the context provided is sufficient for a simple one-parameter tool.
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.
Most tools have distinct purposes, but several clusters overlap: domain_facts, page_meta, and scrape all return page title information, and search_verify, hallucination_check, and sweep all target claim validation. The descriptions usually clarify the use case, but the boundaries are not always obvious.
All names use lowercase snake_case, so there is a baseline consistency, but the pattern is mixed: bare verbs like scrape, summarize, and sweep sit alongside noun+noun forms like domain_facts and noun+verb forms like entity_find. The names are readable but do not form a predictable verb_noun API convention.
At 26 tools, this is heavy and above the typical well-scoped 3-15 range, though the server is explicitly positioned as a broad shelf of paid utilities. Many tools are small one-purpose endpoints, so the count feels more like a catalog than a focused suite, but it is not an extreme mismatch.
The shelf covers the major advertised areas: web page analysis, research verification, text guards and NLP, blockchain reads, and image generation. There are some gaps such as no web search and no transaction sending, but agents can typically work around them or pair this with another server.