Agentic Atlas

Orient in the Atlas

atlas_orient

Read-onlyIdempotent

Discover canonical identity from an ordinary-language query — the entry point when no canonical id is held. Ranked: identity fields and sealed claims decide candidacy, Section text only when no identity field matches; ordered by identity score, then Section score, then how many words matched, then manifest position. Node candidates carry id, status, Hook, and disclosure class; Decision and term candidates carry exactly a read address and Hook. A term's Hook is its full sealed definition. Results are paged. A miss is a successful empty payload.

Input Schema

TableJSON Schema

Name	Required	Description
`kind`	No	Restrict to 'pattern', 'concept', 'example', or 'decision', or 'term'; any kind excludes Roadmap entries. Decision and term candidates carry directly readable addresses.
`bound`	No	Candidates per page, 1-8.
`query`	No	Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies, each word weighed by how few subjects carry it in an identity field. A Section match orders a candidate but makes one only when no subject matches in an identity field, so total counts the candidates, not every subject a word touches. With kind='decision', the searchable identity is the raw canonical id, title, and complete sealed Decision body. With kind='term', the canonical glossary key and sealed definition are searched. Empty lists every subject of the selected kind.
`cursor`	No	scope.next_cursor from a prior atlas_orient page; repeat the same other arguments.
`status`	No	One status-ladder rung; published subjects are 'fleshed' or 'stable'.
`expected_revision`	No	A prior payload's 'coherence'; 'revision_changed' refuses a moved Release.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes
`scope`	Yes
`coherence`	Yes
`projection`	Yes
`payload_class`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedSep 30, 2026
- addedInput schema / properties / query / anyOf
```
Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
```
- addedInput schema / properties / query / default
```
Added value: +null
```
- removedInput schema / properties / query / type
```
Removed value: -"string"
```
- removedInput schema / required
```
Removed value: -[
-  "query"
-]
```

Changed3 schema fields changedSep 7, 2026

changedInput schema / properties / kind / description

Previous value: -"Restrict to 'pattern', 'concept', or 'example'; excludes Roadmap entries."New value: +"Restrict to 'pattern', 'concept', 'example', or 'decision', or 'term'; any kind excludes Roadmap entries. Decision and term candidates carry directly readable addresses."

changedInput schema / properties / query / description

Previous value: -"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies, each word weighed by how few subjects carry it in an identity field. A Section match orders a candidate but makes one only when no subject matches in an identity field, so total counts the candidates, not every subject a word touches. Empty lists every subject."New value: +"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies, each word weighed by how few subjects carry it in an identity field. A Section match orders a candidate but makes one only when no subject matches in an identity field, so total counts the candidates, not every subject a word touches. With kind='decision', the searchable identity is the raw canonical id, title, and complete sealed Decision body. With kind='term', the canonical glossary key and sealed definition are searched. Empty lists every subject of the selected kind."

changedOutput schema / properties / projection / const

Previous value: -"agent-projection/v5"New value: +"agent-projection/v6"

Changed1 schema field changedSep 5, 2026

changedInput schema / properties / query / description

Previous value: -"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies; Section text is searched only when no subject matches in an identity field, and total counts subjects with at least one matching term. Empty lists every subject."New value: +"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies, each word weighed by how few subjects carry it in an identity field. A Section match orders a candidate but makes one only when no subject matches in an identity field, so total counts the candidates, not every subject a word touches. Empty lists every subject."

Changed2 schema fields changedSep 2, 2026

changedInput schema / properties / query / description

Previous value: -"Ordinary design vocabulary, matched case-insensitively against canonical ids, titles, Hooks, and published Section headings and bodies; empty lists every subject."New value: +"Ordinary design vocabulary. Stopwords are dropped and each remaining word matches whole tokens (a word of four or more characters also matches longer tokens it begins) in canonical ids, titles, Hooks, sealed Card claims, and published Section headings and bodies; Section text is searched only when no subject matches in an identity field, and total counts subjects with at least one matching term. Empty lists every subject."

changedOutput schema / properties / projection / const

Previous value: -"agent-projection/v4"New value: +"agent-projection/v5"

Changed1 schema field changedAug 26, 2026
- changedOutput schema / properties / projection / const
```
Previous value: -"agent-projection/v3"New value: +"agent-projection/v4"
```

Changed1 schema field changedAug 26, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "coherence": {
+      "type": "string"
+    },
+    "data": {
+      "type": "object"
+    },
+    "payload_class": {
+      "enum": [
+        "orient"
+      ],
+      "type": "string"
+    },
+    "projection": {
+      "const": "agent-projection/v3"
+    },
+    "scope": {
+      "type": "object"
+    }
+  },
+  "required": [
+    "projection",
+    "coherence",
+    "payload_class",
+    "scope",
+    "data"
+  ],
+  "type": "object"
+}

Changed6 schema fields changedAug 25, 2026

changedInput schema / properties / bound / description

Previous value: -"Maximum candidates per page, 1-8 (default 3)."New value: +"Candidates per page, 1-8."

changedInput schema / properties / cursor / description

Previous value: -"Opaque continuation token from a previous atlas_orient payload's 'scope.next_cursor'. Repeat the same arguments alongside it; a cursor minted for a different request or a different Release is refused with 'invalid_argument'."New value: +"scope.next_cursor from a prior atlas_orient page; repeat the same other arguments."

changedInput schema / properties / expected_revision / description

Previous value: -"Optional coherence marker: the Release version (for example 'v1.0.2') read off any previous payload's 'coherence' field. Omit on a first call. When carried, a promotion that has moved the active Release off this marker is refused with the 'revision_changed' error rather than silently answered from a different Release."New value: +"A prior payload's 'coherence'; 'revision_changed' refuses a moved Release."

changedInput schema / properties / kind / description

Previous value: -"Restrict candidates to one node kind: 'pattern', 'concept', or 'example'. Roadmap entries carry no kind, so any kind filter excludes them."New value: +"Restrict to 'pattern', 'concept', or 'example'; excludes Roadmap entries."

changedInput schema / properties / query / description

Previous value: -"Ordinary design vocabulary naming the problem or subject (for example 'context window budget'). Terms are split on non-alphanumeric characters and matched case-insensitively against canonical ids, titles, Hooks, and published Section headings and bodies. Section text is searched only when those identity fields produce no candidates, and a body-only match requires every query term. An empty string lists every subject in manifest order."New value: +"Ordinary design vocabulary, matched case-insensitively against canonical ids, titles, Hooks, and published Section headings and bodies; empty lists every subject."

changedInput schema / properties / status / description

Previous value: -"Restrict candidates to one maturity rung of the corpus status ladder; published subjects sit at 'fleshed' or 'stable'."New value: +"One status-ladder rung; published subjects are 'fleshed' or 'stable'."

Changed1 schema field changedAug 25, 2026

changedInput schema / properties / query / description

Previous value: -"Ordinary design vocabulary naming the problem or subject (for example 'context window budget'). Terms are split on non-alphanumeric characters and matched case-insensitively; an empty string lists every subject in manifest order."New value: +"Ordinary design vocabulary naming the problem or subject (for example 'context window budget'). Terms are split on non-alphanumeric characters and matched case-insensitively against canonical ids, titles, Hooks, and published Section headings and bodies. Section text is searched only when those identity fields produce no candidates, and a body-only match requires every query term. An empty string lists every subject in manifest order."

Changed6 schema fields changedAug 24, 2026

addedInput schema / properties / bound / description

Added value: +"Maximum candidates per page, 1-8 (default 3)."

addedInput schema / properties / cursor / description

Added value: +"Opaque continuation token from a previous atlas_orient payload's 'scope.next_cursor'. Repeat the same arguments alongside it; a cursor minted for a different request or a different Release is refused with 'invalid_argument'."

addedInput schema / properties / expected_revision / description

Added value: +"Optional coherence marker: the Release version (for example 'v1.0.2') read off any previous payload's 'coherence' field. Omit on a first call. When carried, a promotion that has moved the active Release off this marker is refused with the 'revision_changed' error rather than silently answered from a different Release."

addedInput schema / properties / kind / description

Added value: +"Restrict candidates to one node kind: 'pattern', 'concept', or 'example'. Roadmap entries carry no kind, so any kind filter excludes them."

addedInput schema / properties / query / description

Added value: +"Ordinary design vocabulary naming the problem or subject (for example 'context window budget'). Terms are split on non-alphanumeric characters and matched case-insensitively; an empty string lists every subject in manifest order."

addedInput schema / properties / status / description

Added value: +"Restrict candidates to one maturity rung of the corpus status ladder; published subjects sit at 'fleshed' or 'stable'."

First observedAug 24, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds real behavioral context: results are paged, and 'a miss is a successful empty payload' tells the agent not to treat zero results as an error. The ranking cascade (identity score, Section score, word matches, manifest position) is also non-obvious behavior worth disclosing.

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?

Purpose is front-loaded and the length is defensible for a six-parameter ranked search, but the prose is dense and jargon-laden ('Hook', 'sealed claims', 'disclosure class', 'manifest position') without definition. The candidate-shape sentences also restate what the schema's kind description already says about decision/term addresses.

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 explaining, and the safety profile is covered by annotations. The description still supplies ranking logic, paging, and empty-result semantics, leaving only the undefined Atlas vocabulary as a residual gap.

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%, so the schema already carries parameter meaning and the baseline is 3. The description adds ranking context but no per-parameter syntax or format detail beyond what the schema states.

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 specific verb and resource — 'Discover canonical identity from an ordinary-language query' — and gives scope via 'the entry point when no canonical id is held', which implicitly separates it from id-based siblings like atlas_navigate and atlas_read. It never names those siblings, so differentiation must be inferred.

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?

Provides a clear selection condition: use this when no canonical id is held, implying the navigate/read siblings are for when one is. No explicit exclusions or named alternatives, so it stops short of the top band.

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

All Agentic Atlas 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.

Resources

Need Help?