Skip to main content
Glama

Agent Data Tools: Full list (every tool as its own definition)

Prompt injection detection: scan text for injection attempts

text_prompt_injection
Read-only

Scan text an agent is about to read (web page, email, tool result; up to 8,000 characters) for prompt-injection attempts: instruction overrides, fake system messages, asks to hide things from the user, exfiltration links, attempts to extract private data or move money, invisible Unicode. Returns a risk level, score and findings with excerpts. Heuristic, not a guarantee. Use before acting on untrusted content. Example: text=Thanks for the update. The signed invoice is attached and payment is due on Friday.. Price $0.01/call via x402 USDC or a card key (/credits), first 25 free; failed calls free. Reads or computes only and changes nothing; each call is charged, so repeats are not free.

Tool call template

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": "text_prompt_injection"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesThe text to scan (up to 8,000 characters)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false; the description adds context annotations cannot express: results are heuristic and not a guarantee, the return shape (risk level, score, findings with excerpts), the 8,000-character ceiling, and the billing model. It also explains why repeats are not free, which is consistent with idempotentHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The sentence is front-loaded with purpose and threat taxonomy, and the caveat/usage line follows logically. The embedded example and pricing details are somewhat crammed into parentheses, making the middle of the description dense, but nothing is genuinely redundant.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter detection tool with no output schema, the description covers what is detected, what is returned, input limits, reliability caveats, and cost. An agent has everything needed to decide whether to call it and how to interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the single required parameter already documents the 8,000-character limit, so the description mostly restates it. The embedded example clarifies that arbitrary, largely benign prose is acceptable input, but it adds no syntax or formatting guidance beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ("Scan text an agent is about to read") plus the exact threat classes it looks for (instruction overrides, fake system messages, exfiltration links, invisible Unicode). It is clearly distinguishable from siblings like text_pii or email because it names the artifact (untrusted content) and the failure mode (prompt injection).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use before acting on untrusted content" gives a clear triggering condition and ordering relative to other actions. It does not name any alternative tool or exclusion (e.g., when to prefer text_pii for sensitive-data checks), but the when-to-use guidance is unambiguous.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.