Skip to main content
Glama

Link rot scan and notarized archive — Atom

Link rot scan and notarized archive

link_rot_scan_and_notarized_archive
Read-onlyIdempotent

Submit a link-integrity evidence manifest (scan posture, declared link rows with observed statuses, archive captures, canonicalization, notarization records, serving and repair records); get a deterministic LINK_INTEGRITY_SOUND / LINK_INTEGRITY_UNSOUND / INSUFFICIENT_EVIDENCE verdict across six sections, including computed archived/notarized-citation and rotted-citation-repaired checks, with per-check evidence. Audits declared scan evidence; it does not fetch URLs.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "link_rot_scan_and_notarized_archive"
  }
}

Input Schema

NameRequiredDescriptionDefault
scanNoScan-coverage evidence (scheduled, statuses and content hashes recorded, cadence current).
siteNoSite the scan covers.
linksNoDeclared link rows with observed statuses, capture and notarization fields.
repairNoRepair evidence (repairs logged, no silent drops).
archiveNoArchive-capture evidence (format, fallback chain, cite-time capture).
servingNoHonest-serving evidence (as-seen views, provenance badge, never presented as current).
complianceNoCompliance evidence (robots/ToS, rate limits, no access-control bypass).
notarizationNoNotarization evidence (SHA-256, RFC 3161 / transparency-log timestamps, verification recipe).
canonicalizationNoCanonicalization evidence (trackers stripped, redirects resolved, dedupe by hash).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine value beyond that: the tool is deterministic, evaluates declared evidence rather than fetching, produces three named verdicts across six sections, and returns per-check evidence with computed archived/notarized and repaired-citation checks. It stops short of saying what makes evidence insufficient or what the response envelope looks like.

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?

Front-loaded with the action and outcome, and no sentence is wasted. The opening sentence is however a long parenthetical enumeration of seven record categories, which is dense to parse, and the external SERVICE.md reference is a pointer rather than content.

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 nine-parameter, deeply nested audit tool with no output schema, the description still conveys the verdict vocabulary, the six-section structure, and the computed checks. The main gap is that the section names and the sufficiency bar for INSUFFICIENT_EVIDENCE are not spelled out and are instead delegated to an external SERVICE.md.

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% and all nine nested properties carry their own descriptions, so the schema does the heavy lifting. The description only loosely maps manifest content areas (scan posture, link rows, archive captures, canonicalization, notarization, serving, repair) to the verdict sections, and defers the field table to 'the atom's SERVICE.md', which adds no in-band meaning.

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 ('Submit a link-integrity evidence manifest') plus the exact output ('deterministic LINK_INTEGRITY_SOUND / LINK_INTEGRITY_UNSOUND / INSUFFICIENT_EVIDENCE verdict across six sections'), and closes with an explicit scope negation: 'Audits declared scan evidence; it does not fetch URLs.' An agent can tell exactly what goes in and what comes out.

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?

The final clause gives a clear when-not signal ('it does not fetch URLs'), which prevents an agent from misusing it as a crawler/checker. It lacks any statement of prerequisites or an alternative tool to use when live fetching is actually needed, but no siblings exist to route to, so this is close to complete.

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.