TeamShared

memory_session_ensure

One-call session bootstrap: recover the active session or open one.

Replaces the memory_state_get → memory_session_close → memory_session_open → memory_state_set ritual. Reuses the session in the conversation/active-session state pointer when it is still open and owned by the caller; otherwise closes it (distilling) and opens a fresh one, updating state. Returns {session_id, agent, resumed, soul, soul_linked, profile}. When the bearer is linked to a human account, soul is their private compressed identity block for this org (may be empty string if not yet written). profile is the same token-capped bootstrap object as memory_profile_get. When playbook_slug or a work_id with a bound slug resolves, also returns playbook {name, description, body_md, slug} (its cited skills listed by name and when to load them with memory_skill_get, not their bodies; capped) on both fresh and resume paths. Also org + bound (alias session_bound) + bound_scope. bound is the MCP org-session overlay, not GitHub: false on a normal /mcp session still writes to the token's org. On unbound /mcp, a user account with several orgs may include warnings suggesting org_bind(slug=...) (CLI teamshared org bind is optional). Optional auto_recall=true attaches budgeted recall hits (same provenance citation shape as memory_recall) when user= and/or topic= is set (thin-client bootstrap). Prefer an explicit memory_recall for keyword anchors.

Input Schema

Name	Required	Description
`ttl`	No	Session TTL in seconds (default from server config)
`repo`	Yes	Workspace slug (absolute path with leading / removed and / replaced by -). Keys the conversation/active-session state pointer.
`user`	No	Substantive user request for this turn. When set, appended as the user turn in the same call (replaces a separate memory_session_append).
`agent`	No	Override agent identity
`fresh`	No	Force rotation: close any stored session (queueing distillation) and open a new one. Pass true on the first turn of a new chat.
`topic`	No	What this session is about (used when opening a new one)
`github`	No	GitHub owner/repo; distilled memories inherit the tag
`work_id`	No	Work item UUID. When set and playbook_slug is omitted, that item's playbook_slug is injected on the ensure payload.
`namespace`	No	Limit the attached profile facts/episodes to this org-allowlisted container. Omit for shared-org profile. Invalid/unknown slugs fail.
`auto_recall`	No	Opt-in thin-client bootstrap: when true and user= and/or topic= is set, run a budgeted memory_recall (k=5, explain=false, short deadline) over that text and attach hits as auto_recall. Missing both skips without error. Default false — existing callers are unchanged. Prefer an explicit memory_recall with a short keyword anchor; this is not a replacement.
`playbook_slug`	No	Named playbook to attach (wins over the work item's slug). Unset/missing/cross-org omits playbook — never dumps the catalog.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 22, 2026

addedInput schema / properties / auto_recall

Added value: +{
+  "default": false,
+  "description": "Opt-in thin-client bootstrap: when true and user= and/or topic= is set, run a budgeted memory_recall (k=5, explain=false, short deadline) over that text and attach hits as auto_recall. Missing both skips without error. Default false — existing callers are unchanged. Prefer an explicit memory_recall with a short keyword anchor; this is not a replacement.",
+  "type": "boolean"
+}

Changed1 schema field changedSep 16, 2026

addedInput schema / properties / namespace

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Limit the attached profile facts/episodes to this org-allowlisted container. Omit for shared-org profile. Invalid/unknown slugs fail."
+}

Changed2 schema fields changedSep 3, 2026

addedInput schema / properties / playbook_slug

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Named playbook to attach (wins over the work item's slug). Unset/missing/cross-org omits playbook — never dumps the catalog."
+}

addedInput schema / properties / work_id

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Work item UUID. When set and playbook_slug is omitted, that item's playbook_slug is injected on the ensure payload."
+}

First observedAug 18, 2026

TDQS

A4.2/5.0

Behavior5/5

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

With no annotations, the description carries the whole burden and does: it discloses the destructive side effect ('otherwise closes it (distilling)'), the ownership condition ('still open and owned by the caller'), the state-pointer mutation, and the org-binding subtlety ('``bound`` is the MCP org-session overlay, not GitHub: false on a normal ``/mcp`` session still writes to the token's org'), plus the warnings/org_bind path. This is exactly the behavior an agent cannot infer from the schema.

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 correctly front-loaded, but the body drifts into dense fragments ('Also ``org`` + ``bound`` (alias ``session_bound``) + ``bound_scope``') and spends several sentences on return-value detail for a tool that has an output schema. The org-binding aside is important but buried mid-paragraph.

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?

For an 11-parameter, side-effecting bootstrap tool with no annotations and a rich payload, the description covers side effects, ownership, return shape and alternatives. It still omits failure behavior (unknown namespace/repo, TTL expiry) and the cost of triggering distillation, which leaves a small completeness 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 already 100%, so the baseline is 3. The description restates the semantics of auto_recall and playbook_slug/work_id in prose, but that content is duplicated in the schema rather than adding non-obvious meaning (no constraints on ttl, namespace failure modes, or repo key format beyond what the schema says).

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

Purpose5/5

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

States a specific verb and resource ('One-call session bootstrap: recover the active session or open one') and explicitly frames itself against the four siblings it replaces (memory_state_get → memory_session_close → memory_session_open → memory_state_set). An agent can distinguish this from memory_session_get/open without opening a schema.

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 a clear context ('recover the active session or open one') and names the ritual it supersedes, plus a targeted exclusion: 'Prefer an explicit memory_recall for keyword anchors' when auto_recall is tempting. It does not cover the remaining neighbors (memory_session_get, memory_session_append) or when not to bootstrap at all, so it stops short of full when/when-not guidance.

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

All TeamShared tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.