Skip to main content
Glama

Caelara Shield

shield_scan_prompt

Screen untrusted text before it reaches a model: injection patterns, hidden characters, PII and secrets, with an allow/review/block verdict (0.015 USDC per call)

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": "shield_scan_prompt"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesUntrusted input text (max 200000 characters)
redactNoReturn sanitized_text with PII and secrets masked (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It usefully discloses the three verdict tiers and a per-call price (0.015 USDC), which is real behavioral context an agent can plan around. It does not say whether the input text is logged or retained, what happens on error or timeout, or whether the call is a pure read.

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

Conciseness5/5

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

A single sentence with the action, the detection scope, the verdict model and the price, front-loaded with the verb. Nothing is padding.

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

Completeness3/5

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

For a two-parameter screening tool with no annotations and no output schema, the description covers purpose and verdict tiers but leaves the response shape underspecified — there is no mention of a score, matched-pattern list, or how sanitized_text is returned. An agent knows what it does but not precisely what comes back.

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 description coverage is 100%, so both parameters are already documented in the schema, setting the baseline at 3. The description's mention of PII and secrets partially explains why the redact flag exists but adds no syntax or interaction detail beyond the schema.

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

Purpose4/5

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

The description pairs a specific verb ("Screen") with a specific resource ("untrusted text") and enumerates what it detects (injection patterns, hidden characters, PII, secrets) plus the output verdict. "Before it reaches a model" implicitly separates it from output-side siblings like shield_validate_output, 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.

Usage Guidelines3/5

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

"Before it reaches a model" establishes the point in the pipeline where this tool applies, which is genuine usage context. However, there are no exclusions, no statement of when to prefer shield_audit_token or shield_validate_output, and no prerequisites (auth, quota) are mentioned.

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.

Resources