Skip to main content
Glama
Sign In

GREENLANDAI

by ai.greenlandai
OverviewDiscussionsAdmin

contribute_relations

Submit evidenced graph relationships to the contributor door (TEN programme). Each relation needs subject, relation, object, a real source_url and a verbatim quote from it. Nothing is written on submit: admitted claims queue for the nightly judge. Send your enabled gai_ key as X-API-Key.

Input Schema

NameRequiredDescriptionDefault
entitiesNoNew entities proposed alongside a relation that references them; never accepted on their own.
relationsYesThe relationships to submit.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • removedInput schema / properties / entities / default
      Removed value: -null
    • removedInput schema / properties / entities / title
      Removed value: -"Entities"
    • changedInput schema / properties / relations / description
      Previous value: -"The relationships to submit. Each item: subject, relation, object, source_url (a real http(s) page), quote (a verbatim passage of 15+ characters from that page stating it); optional subject_type, object_type."New value: +"The relationships to submit."
    • removedInput schema / properties / relations / title
      Removed value: -"Relations"
    • removedInput schema / title
      Removed value: -"contribute_relationsArguments"
    • removedOutput schema / title
      Removed value: -"contribute_relationsDictOutput"
  2. Changed2 schema fields changed
    • addedInput schema / properties / entities / description
      Added value: +"New entities proposed alongside a relation that references them; never accepted on their own."
    • addedInput schema / properties / relations / description
      Added value: +"The relationships to submit. Each item: subject, relation, object, source_url (a real http(s) page), quote (a verbatim passage of 15+ characters from that page stating it); optional subject_type, object_type."
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "title": "contribute_relationsDictOutput",
+  "type": "object"
+}
  4. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Goes well past the annotations by disclosing the asynchronous lifecycle ('Nothing is written on submit: admitted claims queue for the nightly judge'), the evidence bar (real source_url plus verbatim quote), and the auth mechanism (X-API-Key). These are exactly the traits an agent cannot infer from readOnlyHint=false, idempotentHint=false, or destructiveHint=false.

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 action, then requirements, then the async caveat, then auth. Every sentence carries distinct information with no repetition of the title or schema.

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?

An output schema exists so return values need no explanation, and the description covers auth, evidence requirements, and deferred adjudication. It is only slightly short of complete, omitting rejection handling and the role of the 'entities' parameter, though the schema documents entities.

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%, so the baseline is 3. The description still adds value: the schema only types 'relations' as an array of open objects, while the description names the per-item fields (subject, relation, object, source_url, quote) and insists the quote be verbatim, which the schema does not convey.

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?

'Submit evidenced graph relationships' gives a specific verb plus resource, and the 'contributor door (TEN programme)' scopes it. It is distinguishable from contribute_receipts by the resource named, though the sibling is never explicitly contrasted.

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

Usage Guidelines3/5

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

Usage is implied: the description makes clear this is the submission path for graph relations requiring evidence, and states a precondition (an enabled gai_ key). However, it never routes the agent against alternatives such as contribute_receipts or contribute_submissions, leaving the choice to inference.

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

All GREENLANDAI toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources