Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Intel Snapshot Ingest

delimit_intel_snapshot_ingest

Store research snapshots with source and author provenance in the intel store for later replay and attestation.

Instructions

Store a research snapshot with provenance in the intel store.

When to use: to ingest research / signal data with provenance (source, author) for later replay or attestation. When NOT to use: to register a dataset (use delimit_intel_dataset_register) or query existing snapshots (delimit_intel_query).

Sibling contrast: delimit_intel_dataset_register declares; delimit_intel_query reads; this writes new snapshots.

Side effects: writes a snapshot record via backends.tools_data.intel_snapshot_ingest. Coerces data and provenance from JSON strings to dicts via _coerce_dict_arg.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataYesSnapshot data (JSON-serializable dict or JSON string). Required.
provenanceNoOptional provenance metadata (source, author, etc.).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv4.7.9
    • changedInput schema / properties / data / description
      Previous value: -"Snapshot data (any JSON-serializable dict)."New value: +"Snapshot data (JSON-serializable dict or JSON string). Required."
  2. Changed6 schema fields changedv4.5.5
    • removedInput schema / properties / data / additionalProperties
      Removed value: -true
    • addedInput schema / properties / data / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "additionalProperties": true,
+    "type": "object"
+  }
+]
    • addedInput schema / properties / data / description
      Added value: +"Snapshot data (any JSON-serializable dict)."
    • removedInput schema / properties / data / type
      Removed value: -"object"
    • changedInput schema / properties / provenance / anyOf
      Previous value: -[
-  {
-    "additionalProperties": true,
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "type": "string"
+  },
+  {
+    "additionalProperties": true,
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / provenance / description
      Added value: +"Optional provenance metadata (source, author, etc.)."
  3. First observedv0.1.0

TDQS

A4.7/5.0
Behavior4/5

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

The annotations already indicate this is not read-only and not destructive. The description goes beyond that by disclosing the side effect of writing a snapshot record via a specific backend and explaining that data and provenance are coerced from JSON strings to dicts via _coerce_dict_arg. This adds useful behavioral detail, though it does not fully address idempotency or failure semantics.

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

Conciseness5/5

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

The description is well-structured with clear sections: purpose, when to use, when not to use, sibling contrast, and side effects. Every sentence contributes useful information, and the main purpose is front-loaded.

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

Completeness5/5

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

For a two-parameter tool with full schema descriptions, an output schema, and safety annotations, the description covers purpose, usage boundaries, sibling relationships, side effects, and parameter coercion behavior. An agent has enough information to select and invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the input schema already documents both parameters. The description adds meaningful value by mentioning the JSON-string-to-dict coercion behavior, which is not obvious from the schema alone and directly affects how callers can pass data and provenance.

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?

The description states a specific verb and resource: 'Store a research snapshot with provenance in the intel store.' It further distinguishes itself from the closely related siblings delimit_intel_dataset_register and delimit_intel_query, making the tool's purpose immediately unambiguous.

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

Usage Guidelines5/5

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

The description provides explicit 'When to use' and 'When NOT to use' guidance, names the alternative tools to use instead, and includes a sibling contrast ('register declares; query reads; this writes'). An agent can confidently decide whether this tool is the right choice.

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

Deploy Server

Other Tools