goldseam

Add to My Selfie

add_to_my_selfie

Read-only

Record what the person said, in their own words, and the statements you propose from it. Each description names the topics it touched (question keys or grouping ids from make_my_selfie) and, for a life event, its category and life period. Each proposed statement names its origin and the key phrases carrying the knowledge, skill or ability; the KSA classifier and Dictionary connect each phrase, and unresolved or ambiguous phrases are returned for you to clarify with the person. Proposed statements are not affirmed.

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": "add_to_my_selfie"
  }
}

Input Schema

Name	Required	Description
`package`	Yes	The package the last GoldSeam Selfie answer returned (goldribbon_package_v1 with its selfie_interview part). Keep it for the person and send it back whole; GoldSeam keeps no copy.
`position`	No	Where the conversation is: group, question_key, note
`interests`	No	What the person says they want to explore or pursue, in their own words
`skip_topics`	No
`descriptions`	No
`proposed_statements`	No

Output Schema

Name	Required	Description
`limits`	No	What this answer could not do, each { code, statement }
`status`	No	What happened, or needs_attention with a problem
`package`	No	The person's package with the interview; absent when the call could not use it
`problem`	No	When status is needs_attention: code, statement, what_to_do
`contract`	Yes
`progress`	No
`proposed`	No
`statement`	Yes
`next_actions`	No
`not_recorded`	No
`awaiting_response`	No
`interests_recorded`	No
`needs_clarification`	No
`descriptions_relinked`	No	Descriptions already recorded that gained a link to the exploration that brought them back: description_id, explored_id

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedNov 3, 2026

addedInput schema / properties / descriptions / items / properties / prompted_by_exploration

Added value: +{
+  "description": "When an exploration's question brought this back: { explored_id } from explore_from_my_selfie (or { code, kind }). The exploration stays linked to this description and to the statements proposed from it. For a description already recorded, send its same words and topics with the new prompted_by_exploration: the link is added beside any earlier one, carried to its statements, and its words are unchanged.",
+  "type": "object"
+}

addedInput schema / properties / interests

Added value: +{
+  "description": "What the person says they want to explore or pursue, in their own words",
+  "items": {
+    "properties": {
+      "channel": {
+        "description": "How the person said it; text when omitted",
+        "enum": [
+          "text",
+          "voice",
+          "avatar"
+        ],
+        "type": "string"
+      },
+      "explored_id": {
+        "description": "Optional: the explored possibility it names, from explore_from_my_selfie",
+        "type": "string"
+      },
+      "words": {
+        "description": "The person's own words",
+        "type": "string"
+      }
+    },
+    "required": [
+      "words"
+    ],
+    "type": "object"
+  },
+  "type": "array"
+}

changedInput schema / properties / proposed_statements / items / properties / origin / description

Previous value: -"The person's own description (from_descriptions: indexes into this call's descriptions, or description_ids) or a document passage (document { evidence_id, passage }). exploration { code } is context only, beside a description: occupational data alone never becomes a statement."New value: +"The person's own description (from_descriptions: indexes into this call's descriptions, or description_ids) or a document passage (document { evidence_id, passage }). exploration { explored_id } (or { code, kind }) is context only, beside a description: occupational data alone never becomes a statement. A description an exploration prompted carries that context to its statements without naming it again."

addedOutput schema / properties / descriptions_relinked

Added value: +{
+  "description": "Descriptions already recorded that gained a link to the exploration that brought them back: description_id, explored_id",
+  "type": "array"
+}

addedOutput schema / properties / interests_recorded
```
Added value: +{
+  "type": "array"
+}
```

AddedNov 3, 2026

TDQS

B3/5.0

Behavior4/5

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

Beyond readOnlyHint=true, the description discloses real behavior: phrases are connected by the KSA classifier and Dictionary, unresolved or ambiguous phrases are returned for clarification, and proposed statements are explicitly not affirmed. That is meaningful state/flow information an agent could not get from the annotation alone, though it stops short of saying whether anything is persisted or how repeated submissions are handled.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core action is front-loaded, but the text is a dense run-on chain of clauses about topics, life events, origins, and classifiers with no paragraph or bullet structure. Every clause carries some information, yet the packing makes the entry point harder to parse than the content warrants.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with six nested parameters, an output schema, and only one annotation, the description is adequate on descriptions and proposed statements but silent on interests, skip_topics, and position. An agent could call it correctly for the main path but would be guessing about the skip and interest paths.

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 50%, and the description adds genuine meaning for `descriptions.topics` (question keys or grouping ids from make_my_selfie) and for `proposed_statements.phrases` (key phrases routed to the KSA Dictionary). However, `interests`, `skip_topics`, and `position` are never mentioned, so the description only partially compensates for the coverage gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description says to "Record what the person said, in their own words, and the statements you propose from it," which is a verb plus an implied resource, but it never names the resource (the selfie package) directly — that only appears in the tool name and schema. A reader can infer it appends descriptions and proposed statements to a selfie package, but the opening sentence is abstract and jargon-laden rather than stating the operation crisply.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance: the description never says to call this after make_my_selfie returns a package, nor when to prefer it over explore_from_my_selfie or respond_to_my_statements. References to make_my_selfie question keys and explore_from_my_selfie ids imply a workflow, but the sequencing is left for the agent to reconstruct from parameter descriptions.

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.