goldseam

Draft My Claims

draft_my_claims

Read-only

Make the credit claims a person's learning supports, from their package. The answer names its path in path. The GoldSeam path (goldseam): when the package holds a GoldSeam Selfie (make_my_selfie, add_to_my_selfie, respond_to_my_statements) with at least one statement the person affirmed, even beside a document Selfie, each affirmed statement is one claim in the person's own words, with the words it came from and its KSA Dictionary identifiers. Nothing is drafted, no AI is called and no confidence number is assigned; a statement they reject or remove in their Selfie is no longer a claim. The OpenAI path (openai): a package holding only a document Selfie (after my_selfie_ksa_view) gets drafted claims, each quoting the document it rests on. They are drafts for the person to keep, affirm or decline (set each claim's confidence to ratified, affirmed or declined in the package); the AI never affirms a claim. Give the school they are thinking of as school so its catalog is made ready for suggest_credit_for_my_learning. Nothing is stored: the answer returns the package for the agent to keep.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "package": "<package>"
    },
    "name": "draft_my_claims"
  }
}

Input Schema

Name	Required	Description
`school`	No	Optional: the school they are thinking of, a name or IPEDS UNITID; its catalog is made ready for the suggestions
`package`	Yes	The goldribbon_package_v1 object an earlier GoldRibbon answer returned. Keep it for the person and send it back whole; GoldSeam keeps no copy.
`language`	No
`aspiration`	No	Optional: what the person is aiming for

Output Schema

Name	Required	Description
`path`	No	The path this answer took: goldseam (the GoldSeam Selfie's affirmed statements, no AI call) or openai (the document Selfie)
`claims`	No	The claims made by this call, each with summary, source_fragment, kind, evidence_tier and recommendation_mode. On the GoldSeam path one per affirmed statement, with statement_id, identifiers and confidence affirmed, and no confidence_floor; on the OpenAI path drafted, with confidence drafted
`counts`	No	affirmed_statements on the GoldSeam path; drafted, answered_kept on the OpenAI path
`limits`	No	What this answer could not do, each { code, statement }
`package`	No	The person's package, with this service's part filled
`contract`	Yes
`statement`	Yes
`next_actions`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedNov 10, 2026

changedOutput schema / properties / claims / description

Previous value: -"The claims drafted by this call, each with summary, source_fragment, kind, evidence_tier, confidence (drafted) and recommendation_mode"New value: +"The claims made by this call, each with summary, source_fragment, kind, evidence_tier and recommendation_mode. On the GoldSeam path one per affirmed statement, with statement_id, identifiers and confidence affirmed, and no confidence_floor; on the OpenAI path drafted, with confidence drafted"

changedOutput schema / properties / counts / description

Previous value: -"drafted, answered_kept"New value: +"affirmed_statements on the GoldSeam path; drafted, answered_kept on the OpenAI path"

addedOutput schema / properties / path

Added value: +{
+  "description": "The path this answer took: goldseam (the GoldSeam Selfie's affirmed statements, no AI call) or openai (the document Selfie)",
+  "enum": [
+    "goldseam",
+    "openai"
+  ],
+  "type": "string"
+}

AddedSep 22, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Goes well past readOnlyHint=true by disclosing that on the GoldSeam path nothing is drafted and no AI is invoked, that no confidence number is assigned, that rejected or removed statements cease to be claims, and that the AI never affirms a claim. It also states persistence behavior explicitly ('Nothing is stored: the answer returns the package for the agent to keep'), which is exactly the kind of context annotations cannot convey. All of this is consistent with the readOnly annotation.

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?

Purpose is front-loaded in the first sentence, followed by a clean per-path breakdown and a closing persistence/next-step note, so a reader can stop early if needed. Some phrasing is dense and repetitive ('Nothing is drafted...' / 'Nothing is stored...' / 'the AI never affirms a claim'), but each sentence carries distinct operational information rather than filler.

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?

Output schema exists, so return values needn't be spelled out, yet the description still notes 'the answer names its path in `path`' and that the package is returned. Combined with the branch conditions, the non-persistence guarantee, and the confidence-setting contract, an agent has enough to invoke it correctly; only the unmentioned `language` and `aspiration` parameters leave a small hole.

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 coverage is 75%, so the schema already carries most parameter meaning; the description adds a real reason for `school` (its catalog is prepared for suggest_credit_for_my_learning) and reinforces that `package` must be sent back whole. However, `aspiration` and the `language` enum (en/es/fr) are never mentioned, so the description does not compensate for the remaining gap. Baseline 3 fits.

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?

States a concrete verb and resource: it produces 'the credit claims a person's learning supports' from a supplied package, and explicitly splits behavior into a `goldseam` path and an `openai` path so the agent knows what output shape to expect. It does not directly compare itself to any sibling (e.g. suggest_credit_for_my_learning or my_selfie_ksa_view), so differentiation is present only indirectly through the workflow references.

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?

Gives explicit preconditions for each branch: GoldSeam applies when the package holds a Selfie with at least one affirmed statement (even alongside a document Selfie), while the OpenAI path applies only when the package holds solely a document Selfie after my_selfie_ksa_view. It also states the downstream step (give `school` so its catalog is ready for suggest_credit_for_my_learning) and what the person should do with drafts (ratify/affirm/decline). It stops short of saying when NOT to call it or naming an alternative tool outright.

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

All goldseam tools Inspect

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.