Datacron

Overview Schema Source Related Servers Discussions Admin

Start a memory session

session_context

Read-only

Initialize memory-dependent work by returning the current contract, write permissions, bounded live notes, and ranked subject candidates; verify stale sources before relying on them.

Instructions

Start memory-dependent work here. Return the versioned common discipline, effective write capability and bounded live notes. Optional subject finds ranked candidates without repairing the index. Coverage is explicit; candidates never establish a person's identity. Read next pages before relying on incomplete context. Send known_contract_hash only when that exact contract is already in context; a match returns its identity without repeating instructions. Re-verify a source whose freshness is stale, unverified or invalid before relying on it, then set last_verified; a missing freshness field is no verdict.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "session_context"
  }
}

Input Schema

Name	Required	Default
`domain`	No	all
`subject`	No
`max_tokens`	No
`note_paths`	No
`known_contract_hash`	No

Output Schema

Name	Required	Description	Default
`omitted`	No
`runbook`	No
`sources`	No
`contract`	No
`coverage`	No
`evidence`	No
`identity`	No
`truncated`	No
`unavailable`	No
`capabilities`	No
`subject_state`	No
`index_repaired`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedv0.1.20Nov 5, 2026

addedOutput schema / properties / runbook

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "title": "Runbook"
+}

Changed12 schema fields changedv0.1.17Oct 17, 2026
- addedOutput schema / description
```
Added value: +"Bounded initialization; returned context is not a behavior attestation."
```
- removedOutput schema / properties / capabilities / default
```
Removed value: -null
```
- removedOutput schema / properties / contract / default
```
Removed value: -null
```
- removedOutput schema / properties / coverage / default
```
Removed value: -null
```
- removedOutput schema / properties / evidence / default
```
Removed value: -null
```
- removedOutput schema / properties / identity / default
```
Removed value: -null
```
- removedOutput schema / properties / index_repaired / default
```
Removed value: -null
```
- removedOutput schema / properties / omitted / default
```
Removed value: -null
```
- removedOutput schema / properties / sources / default
```
Removed value: -null
```
- removedOutput schema / properties / subject_state / default
```
Removed value: -null
```
- removedOutput schema / properties / truncated / default
```
Removed value: -null
```
- removedOutput schema / properties / unavailable / default
```
Removed value: -null
```

Changed1 schema field changedv0.1.16Oct 1, 2026

addedOutput schema / properties / subject_state

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Subject State"
+}

Changed1 schema field changedv0.1.11Sep 15, 2026

addedInput schema / properties / known_contract_hash

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Known Contract Hash"
+}

Addedv0.1.5Sep 5, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Beyond the readOnlyHint/destructiveHint annotations, it discloses real behavioral traits: output is bounded, coverage is explicitly reported, ranked candidates are explicitly not identity claims, and a contract hash match short-circuits instruction repetition. Two gaps remain: what 'effective write capability' gating means (auth/permission semantics), and the ambiguous 'then set last_verified' clause, which reads like a mutation on a tool annotated readOnlyHint=true — most plausibly a pointer to a sibling like set_frontmatter, but left unclear.

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 size is reasonable and the primary action is front-loaded, but the prose is compressed to the edge of unreadability — 'bounded live notes', 'Coverage is explicit', 'a missing freshness field is no verdict' — with no structure to separate the entry condition from the parameter rules and the freshness workflow. Every sentence carries information, but several need a second parse.

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?

An output schema exists, so not explaining the returned fields is acceptable, and the safety profile is annotation-covered. For a 5-parameter, zero-coverage session entrypoint, however, the description leaves the agent guessing about domain selection, note_paths format, max_tokens units, and what happens when coverage is partial or empty.

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 0%, so the description must carry all parameter meaning, and it only partly does. known_contract_hash is explained precisely and subject is described behaviorally ('finds ranked candidates without repairing the index'), but domain (6 enum values), note_paths, and max_tokens get no explanation at all — max_tokens is only obliquely implied by 'bounded'. Partial compensation, not full.

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?

The opening sentence gives a clear verb and role — 'Start memory-dependent work here' — and the second names the returned bundle (versioned common discipline, effective write capability, bounded live notes), which distinguishes this session-bootstrap tool from the note-level siblings like get_note or list_notes. Clarity is dented by undefined internal jargon ('common discipline', 'effective write capability', 'coverage is explicit'), so an agent knows the shape of the action but not precisely what content it will receive.

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?

It states when to call ('Start memory-dependent work here'), how to treat results ('Read next pages before relying on incomplete context'), and a precise conditional for known_contract_hash ('Send... only when that exact contract is already in context'). It also gives a re-verification workflow for stale/unverified/invalid sources. It never names an alternative sibling tool for simpler single-note needs, which keeps it below a 5.

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