Skip to main content
Glama

proof_certify

Cryptographically certify any AI-generated content with a permanent SHA-256 provenance certificate — tamper-proof, publicly verifiable forever. Perfect for: certifying AI outputs before sharing, audit trails for agent decisions, proving timestamp and authorship of any content. Returns cert_id, permanent verify_url (zambo.dev/proof), and SHA-256 hash. AGENT USE: Call after any important tool result to create a receipt then share the verify_url — any human or agent can verify it at zambo.dev/proof permanently. Free: 5 certs/day. Zambo Pass: unlimited. When to use: call proof_certify when the user's request matches this capability. When not to use: do not call it for unrelated work, missing required inputs, or when a safer read-only route is more appropriate.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
emailNoOptional Zambo Pass email for unlimited certs
labelNoHuman-readable label (e.g. 'ZAMBOT Spark', 'Strategy Plan', 'Agent Decision')
contentYesThe content to certify — AI output, decision, plan, analysis, or any text

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
cert_idNo
verify_urlNo
sha256_hashNo

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": true,
      +  "properties": {
      +    "cert_id": {
      +      "type": "string"
      +    },
      +    "sha256_hash": {
      +      "type": "string"
      +    },
      +    "verify_url": {
      +      "type": "string"
      +    }
      +  },
      +  "type": "object"
      +}
  2. Added

TDQS

A3.8/5.0
Behavior4/5

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

No annotations are provided, so the description carries the full transparency burden. It discloses permanence ('permanent... publicly verifiable forever'), the return payload (cert_id, verify_url, hash), and the quota model ('Free: 5 certs/day. Zambo Pass: unlimited'). It does not address privacy implications of permanent public verification or failure behavior on quota exhaustion, but major behavioral traits are covered.

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

Conciseness3/5

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

The description contains useful behavioral information but is padded with promotional phrasing ('Perfect for:', 'tamper-proof') and a tautological usage line ('call proof_certify when the user's request matches this capability'). The key purpose is front-loaded in the first sentence, but the rest could be tightened without losing meaning.

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?

For a 3-parameter tool with an output schema, the description is fairly complete: it covers use case, trigger, return values, verification URL, and quotas. It stops short of concretely explaining what a 'safer read-only route' would be and does not name the verification sibling, leaving some ambiguity for tool selection. Most information needed to call it correctly is present.

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?

The input schema already documents all three parameters with 100% coverage. The description adds little beyond restating that content is certified; for example, the schema already says content is 'AI output, decision, plan, analysis, or any text.' The only small addition is connecting email to the free-tier/unlimited distinction. This is a baseline score.

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 clearly states a specific verb-resource pair: 'Cryptographically certify any AI-generated content with a permanent SHA-256 provenance certificate.' It also names outputs (cert_id, verify_url, SHA-256 hash) and use cases. However, it does not explicitly distinguish itself from sibling verification tools like zambot_verify, so differentiation is left to inference.

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?

Provides explicit usage guidance: 'Call after any important tool result to create a receipt' and a 'When not to use' section listing exclusions such as unrelated work, missing required inputs, and when a safer read-only route is more appropriate. It gives clear context and exclusions but does not name a specific alternative tool, stopping short of a top score.

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.

TDQS

A3.6/5.0
Disambiguation4/5

Each tool has a fairly distinct purpose (crypto price, lead gen, prompt safety, code audit, etc.) and detailed descriptions. However, zambo_universal is a catch-all router that overlaps with most specific tools, and capability_search/zambot_spark both reference the 100+ tool stack, creating some boundary ambiguity.

Naming Consistency2/5

The naming is inconsistent: some tools use underscore separated verbs (live_price, prompt_shield), while others are single compound words (credithunt, leadsignal) or brand-prefixed phrases (zambo_live, zambot_spark, provibe_audit). There is no clear verb_noun pattern.

Tool Count4/5

10 tools is within the ideal 3-15 range for a multi-purpose server. Each tool serves a different niche, though some like zambo_live are meta-service tools rather than domain features.

Completeness3/5

The server is intentionally a gateway to a '100+ tool stack', so it exposes a small subset plus a universal router to fill gaps. However, individual capabilities are shallow (e.g. single crypto price lookup, single lead gen query) and there are no management or configuration tools, making completeness feel partial.

Resources