Skip to main content
Glama

watch_add

Watch ONE citation or ONE package version instead of checking it once. Send kind ('citation' or 'package') and the subject (a DOI, an arXiv ID or a title; or npm:express@4.18.2). The first check is answered immediately and signed, then re-checked daily for 30 days; every real change (a retraction, a new advisory, a yanked version) is recorded with its own signed receipt. Returns a read URL and a token shown once; optionally send an https webhook and each change is POSTed to it. For a whole list of references under one purchase use watch_portfolio; for a one-off answer that does not need watching, use verify_citation or verify_package. Comes with an Ed25519-signed receipt covering the question, the verdict, the sources and the time, checkable offline against the published key at /.well-known/factstamp-issuer.json — so the check itself can be audited later by someone who was not here.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
kindYesWhat kind of subject this is.
subjectYesThe DOI, arXiv ID or title to watch; for a package, 'express@4.18.2' or 'npm:express@4.18.2'.
webhookNoOptional https URL: each recorded change is POSTed there as JSON.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations cover the safety profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false), and the description adds substantial context: first check answered immediately, re-checked daily for 30 days, changes recorded as signed receipts, webhook POSTs, and a read token shown only once. It does not state rate limits or how to stop a watch, which are the notable remaining gaps.

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 core action and well-ordered (what it does, mechanics, alternatives, signing). The final sentence on Ed25519 receipts and the well-known key URL is dense and could be trimmed, but every sentence carries actionable content.

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?

With no output schema, the description still covers returns (read URL, one-time token) and side effects (daily re-checks, webhook POSTs, signed receipts). Nothing an agent needs to invoke the tool correctly appears to be missing.

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

Parameters4/5

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

Schema coverage is 100%, and the description still adds value by giving concrete subject examples (DOI, arXiv ID, title, 'npm:express@4.18.2') and by explaining that the optional https webhook receives each recorded change as JSON — behavior the schema field only hints at.

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?

The opening sentence states a specific verb and resource with scope: 'Watch ONE citation or ONE package version instead of checking it once.' It immediately distinguishes itself from verify_citation/verify_package (one-off checks) and watch_portfolio (lists), so an agent can route without opening any schema.

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

Usage Guidelines5/5

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

Explicit when-to-use and alternatives are named: 'For a whole list of references under one purchase use watch_portfolio; for a one-off answer that does not need watching, use verify_citation or verify_package.' Both the sibling and the selecting condition are given.

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