Skip to main content
Glama
markmhendrickson

Neotoma

by markmhendrickson
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Local

retrieve_entity_snapshot

Retrieve the current snapshot of an entity with provenance information. Supports historical snapshots via 'at' parameter.

Instructions

Retrieve the current snapshot of an entity with provenance information. Supports historical snapshots via 'at' parameter.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
atNoEvent-time cutoff (ISO 8601). Reconstructs the snapshot from observations whose `observed_at` ≤ this timestamp. Reflects what *happened* by time T, regardless of when the observation was ingested into Neotoma. Use `at_ingested` instead when you need "what did we actually know at time T" semantics.
formatNoResponse text format. `markdown` (default for MCP) returns canonical deterministic markdown for KV-cache stability. `json` returns the raw snapshot payload for programmatic callers.
entity_idNo
at_ingestedNoIngestion-time cutoff (ISO 8601). Reconstructs the snapshot from observations whose `created_at` (row-insertion time) ≤ this timestamp. Excludes backfilled or late-arriving observations that have a past `observed_at` but arrived after this cutoff, preventing look-ahead leaks. When both `at` and `at_ingested` are supplied, both bounds are applied (AND logic): an observation must satisfy `observed_at ≤ at` AND `created_at ≤ at_ingested`.
include_cleared_fieldsNoInclude only selected explicit-null fields with winning provenance; requires complete owned acquisition and an active schema.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.25.0
    • addedInput schema / properties / include_cleared_fields
      Added value: +{
+  "default": false,
+  "description": "Include only selected explicit-null fields with winning provenance; requires complete owned acquisition and an active schema.",
+  "type": "boolean"
+}
  2. Changed2 schema fields changedv0.21.0
    • changedInput schema / properties / at / description
      Previous value: -"ISO 8601 timestamp for historical snapshot reconstruction"New value: +"Event-time cutoff (ISO 8601). Reconstructs the snapshot from observations whose `observed_at` ≤ this timestamp. Reflects what *happened* by time T, regardless of when the observation was ingested into Neotoma. Use `at_ingested` instead when you need \"what did we actually know at time T\" semantics."
    • addedInput schema / properties / at_ingested
      Added value: +{
+  "description": "Ingestion-time cutoff (ISO 8601). Reconstructs the snapshot from observations whose `created_at` (row-insertion time) ≤ this timestamp. Excludes backfilled or late-arriving observations that have a past `observed_at` but arrived after this cutoff, preventing look-ahead leaks. When both `at` and `at_ingested` are supplied, both bounds are applied (AND logic): an observation must satisfy `observed_at ≤ at` AND `created_at ≤ at_ingested`.",
+  "type": "string"
+}
  3. Addedv0.15.0
  4. Removedv0.14.0
  5. Addedv0.12.1
  6. Removedv0.11.0
  7. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries full behavioral burden. 'Retrieve' plus 'snapshot' reasonably implies a non-mutating read, and 'with provenance information' hints at the return content, but it never explicitly declares read-only semantics, nor mentions auth needs, empty/missing-entity behavior, or determinism.

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

Conciseness4/5

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

Two short sentences, front-loaded with the core purpose, with zero filler. The historical-snapshot capability is correctly placed second.

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 retrieval tool with strong schema coverage but no output schema and no annotations, the description is only adequate. It does not describe the shape of the returned snapshot, error/empty behavior, or the format default, leaving those gaps partly uncovered elsewhere.

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 80%, so the schema already documents 'at', 'at_ingested', 'format', and 'include_cleared_fields' in rich detail. The description only restates the 'at' parameter's purpose, adding no syntax or defaults beyond the schema, so the baseline 3 applies.

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 (Retrieve) and resource (current snapshot of an entity) plus the provenance angle, which clearly distinguishes it from the plural 'retrieve_entities' and from 'get_relationship_snapshot'. It never names a sibling explicitly, but the scope is unambiguous.

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

Usage Guidelines3/5

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

The second sentence implies usage for historical snapshots via 'at', giving a hint of when the tool applies. It offers no when-not guidance, no exclusions, and no routing to alternatives like retrieve_entities or the at-vs-at_ingested distinction (which lives only in the schema).

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