Skip to main content
Glama

GAIP Supplier Watch Agent

by io.github.tjcgraham-rgb
OverviewDiscussionsAdmin

Why is my supplier failing?

gaip_supplier_reliability
Read-only

Use this when a supplier agent or API you depend on started failing ("did something change on their side?"). Pass its supplier_url and the failure. Returns the diagnosis plus changes GAIP observed around then (correlated in time, not causation), with receipts. Free, read-only, no account; inputs must be public and non-personal.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
cardNoOptional supplier card / server description you integrated against.
failureNo{code, detail?, http_status?} as for gaip_diagnose_integration_failure.
failuresNoOptional: several failures, each {code, detail}.
protocolNoOmit to infer it from card, transport or the supplier URL path (else UNKNOWN).
transportNoOptional transport you used (e.g. streamable-http, sse, GRPC).
task_classNoOptional: short name of the task, e.g. weather_forecast.
supplier_urlYesPublic https URL of the supplier's agent card, MCP server or API.
lookback_daysNoOptional: days of GAIP observations to look back over.
counterparty_idNoOptional: name of the supplier.
failure_started_atNoOptional: RFC 3339 time the failures started.
data_classificationNoPUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data.PUBLIC

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / card
      Added value: +{
+  "description": "Optional supplier card / server description you integrated against.",
+  "type": "object"
+}
    • changedInput schema / properties / protocol / description
      Previous value: -"A2A, MCP or OPENAPI. Inferred when omitted."New value: +"Omit to infer it from card, transport or the supplier URL path (else UNKNOWN)."
    • changedInput schema / properties / protocol / enum
      Previous value: -[
-  "A2A",
-  "MCP",
-  "OPENAPI"
-]New value: +[
+  "A2A",
+  "MCP",
+  "OPENAPI",
+  "UNKNOWN"
+]
    • addedInput schema / properties / transport
      Added value: +{
+  "description": "Optional transport you used (e.g. streamable-http, sse, GRPC).",
+  "type": "string"
+}
  2. Changed8 schema fields changed
    • addedInput schema / properties / counterparty_id / description
      Added value: +"Optional: name of the supplier."
    • addedInput schema / properties / data_classification / description
      Added value: +"PUBLIC (default) or NON_PERSONAL_PUBLIC. Never send personal data."
    • addedInput schema / properties / failure_started_at / description
      Added value: +"Optional: RFC 3339 time the failures started."
    • addedInput schema / properties / failures / description
      Added value: +"Optional: several failures, each {code, detail}."
    • addedInput schema / properties / lookback_days / description
      Added value: +"Optional: days of GAIP observations to look back over."
    • addedInput schema / properties / protocol / description
      Added value: +"A2A, MCP or OPENAPI. Inferred when omitted."
    • addedInput schema / properties / supplier_url / description
      Added value: +"Public https URL of the supplier's agent card, MCP server or API."
    • addedInput schema / properties / task_class / description
      Added value: +"Optional: short name of the task, e.g. weather_forecast."
  3. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare read-only, non-destructive and non-open-world, but the description adds genuinely new behavioral facts: it is free, requires no account, inputs must be public and non-personal, and results are time-correlated observations rather than causal claims. That last caveat is important for interpretation and is not in any structured field; only rate limits and the meaning of idempotentHint=false (repeated calls may return different observations) are left unstated.

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?

Three sentences, front-loaded with the usage trigger before inputs and traits, so every sentence does work. It is slightly dense with stacked parentheticals and prose asides, but nothing is wasted.

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 11 params, nested objects, and no output schema, the description does the necessary compensating work by summarizing the return ('diagnosis plus changes observed... with receipts'). The one real gap is the missing boundary against gaip_diagnose_integration_failure, which matters given the overlap in inputs and purpose.

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% with 11 well-documented params, so the schema already carries parameter meaning. The description names supplier_url and failure but adds no format, defaults, or constraint detail beyond the schema, making 3 the correct baseline.

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 trigger and outcome: it diagnoses why 'a supplier agent or API you depend on started failing' and returns 'the diagnosis plus changes GAIP observed around then.' That is a clear verb+resource, but it never names or contrasts with its only sibling, gaip_diagnose_integration_failure, which the input schema itself references ('as for gaip_diagnose_integration_failure'), so the supplier-vs-integration boundary is left ambiguous.

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 opens with an explicit selection condition ('Use this when a supplier agent or API you depend on started failing') and even supplies the user's likely phrasing ('did something change on their side?'). There is no when-not guidance and no pointer to the sibling for the alternative case, which keeps it short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All GAIP Supplier Watch Agent toolsInspect
Try in Browser
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources