Skip to main content
Glama

LeadShield Contact Form & B2B Solicitation Blocker

Preview or Save Site Screening Rules

leadshield_configure_spam_policy
DestructiveIdempotent

Preview changes to a connected site's spam rules. Set dryRun to false to save them with write access. Saved rules affect future submissions. Omitted settings are preserved. A successful save returns the policy read back from storage.

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": {
      "site": "<site>"
    },
    "name": "leadshield_configure_spam_policy"
  }
}

Input Schema

NameRequiredDescriptionDefault
siteYesTarget site or client slug.
dryRunNoDefaults to true. Set to false with account write access to save changes.
maxUrlsNoMaximum allowed URLs when blockUrlsInMessage is false.
formTypeNoDefault form-type preset for this site.
blockedKeywordsNoKeywords or phrases that block a submission, matched without regard to case.
allowedCountriesNoAllowed ISO 3166-1 alpha-2 country codes (e.g. ['US', 'CA']).
requiredKeywordsNoAt least one listed phrase must appear in the message, matched without regard to case. An empty list disables this rule.
blockUrlsInMessageNoWhether to block URLs and HTML anchor tags in messages.
allowedPhoneFormatsNoAccept a phone number when it matches any listed format. Supported formats: us-nanp, uk, au, eu, international, e164, any. US_NANP and E164 are accepted aliases. An empty list restores the single-format setting.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / allowedPhoneFormats / description
      Previous value: -"Allowed phone format presets (e.g. ['US_NANP', 'E164'])."New value: +"Accept a phone number when it matches any listed format. Supported formats: us-nanp, uk, au, eu, international, e164, any. US_NANP and E164 are accepted aliases. An empty list restores the single-format setting."
    • changedInput schema / properties / blockedKeywords / description
      Previous value: -"Additional custom keywords or phrases to block in Stage 0."New value: +"Keywords or phrases that block a submission, matched without regard to case."
    • changedInput schema / properties / dryRun / description
      Previous value: -"Defaults to true. Set to false with operator authorization to persist changes."New value: +"Defaults to true. Set to false with account write access to save changes."
    • changedInput schema / properties / formType / enum
      Previous value: -[
      -  "general_inquiry",
      -  "quote_request",
      -  "booking_request",
      -  "b2b_partnership",
      -  "support_ticket",
      -  "careers_application",
      -  "warranty_claim",
      -  "event_registration",
      -  "newsletter_signup",
      -  "feedback_review"
      -]New value: +[
      +  "local_service",
      +  "b2b_saas",
      +  "b2b",
      +  "agency",
      +  "portfolio",
      +  "ecommerce",
      +  "booking",
      +  "quiz",
      +  "real_estate",
      +  "careers",
      +  "newsletter",
      +  "general",
      +  "general_inquiry",
      +  "quote_request",
      +  "booking_request",
      +  "b2b_partnership",
      +  "support_ticket",
      +  "careers_application",
      +  "warranty_claim",
      +  "event_registration",
      +  "newsletter_signup",
      +  "feedback_review"
      +]
    • changedInput schema / properties / requiredKeywords / description
      Previous value: -"Optional keywords where at least one must appear."New value: +"At least one listed phrase must appear in the message, matched without regard to case. An empty list disables this rule."
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true and non-read-only, and the description adds real value on top: the default-dry-run safety, the write-access prerequisite, that saved rules affect future submissions, that omitted fields are preserved rather than cleared, and that a save returns the stored policy. The one gap is that it never frames the change as replacing existing screening behavior, which is precisely what destructiveHint warns about.

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?

Four short sentences, front-loaded with the default (preview) behavior, then the save toggle, then side effects, then the follow-through of omitted settings. Every sentence conveys an actionable fact and none repeats the title or schema verbatim.

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

Completeness4/5

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

With no output schema, the description correctly compensates by telling the agent that a successful save returns the policy read back from storage. For a 9-parameter mutation tool it covers the safety and persistence story well; the only missing piece is what a dry run itself returns (a diff versus the proposed policy), which affects how the agent reports preview results.

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%, so every parameter — including the dryRun default, format aliases, and case-insensitive matching — is already documented in the schema. The description restates the dryRun toggle and the omission-preservation rule without adding syntax or interaction detail beyond the structured fields, so the baseline 3 applies.

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 gives a specific verb and resource ('Preview changes to a connected site's spam rules') and adds that setting dryRun to false saves them, so the read-vs-write duality is explicit. It does not name the read sibling (leadshield_get_spam_policy) that an agent would naturally compare against, so differentiation is implied rather than stated.

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?

It states the condition for the mutating path ('Set dryRun to false to save them with write access') and clarifies that omitted settings are preserved, which is critical when deciding whether to send a partial payload. It stops short of telling the agent to call leadshield_get_spam_policy first to fetch the baseline, an exclusion/order hint that would have earned a 5.

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.