Skip to main content
Glama
total-agent-memory

total-agent-memory

memory_temporal_query

Read-onlyIdempotent

Resolve temporal relationships, calculate durations between dates, normalize natural-language dates, and recall stored memories as of a specific timestamp for time-aware agent reasoning.

Instructions

v11.0 W1-C: deterministic temporal reasoning — Allen interval relations, duration arithmetic (days/weeks/months/years), and natural-language date normalization (en + ru), and historical recall. Pass op=relation|duration_between|normalize|snapshot.

Input Schema

NameRequiredDescriptionDefault
aNoISO datetime — duration_between
bNo
opYes
langNoauto
a_endNo
as_ofNoISO snapshot timestamp
b_endNo
limitNo
queryNoSearch query — snapshot only
anchorNoISO datetime anchor for relative phrases
phraseNoNatural-language date — normalize
a_startNoISO datetime — relation only
b_startNo
projectNoProject filter — snapshot only

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv15.0.0
    • addedInput schema / allOf
      Added value: +[
      +  {
      +    "if": {
      +      "properties": {
      +        "op": {
      +          "const": "snapshot"
      +        }
      +      }
      +    },
      +    "then": {
      +      "required": [
      +        "query",
      +        "as_of"
      +      ]
      +    }
      +  }
      +]
    • addedInput schema / properties / as_of
      Added value: +{
      +  "description": "ISO snapshot timestamp",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / limit
      Added value: +{
      +  "default": 10,
      +  "minimum": 1,
      +  "type": "integer"
      +}
    • changedInput schema / properties / op / enum
      Previous value: -[
      -  "relation",
      -  "duration_between",
      -  "normalize"
      -]New value: +[
      +  "relation",
      +  "duration_between",
      +  "normalize",
      +  "snapshot"
      +]
    • addedInput schema / properties / project
      Added value: +{
      +  "description": "Project filter — snapshot only",
      +  "type": "string"
      +}
    • addedInput schema / properties / query
      Added value: +{
      +  "description": "Search query — snapshot only",
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful context — that results are deterministic and that normalization supports en and ru — but says nothing about what snapshot recall returns, how limit applies, or how partial intervals (a_start/a_end vs a/b) behave.

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 core content is a single sentence, but it is a run-on with repeated 'and … and …' conjunctions, and it leads with the internal build tag 'v11.0 W1-C', which is noise for an agent. The op list is usefully placed at the end but would be better front-loaded.

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

Completeness2/5

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

For a 14-parameter, four-mode tool with no output schema, one sentence is thin: return shapes, per-op parameter applicability, and the meaning of limit/anchor/lang are all left unstated. The description explains the ops but not enough for an agent to invoke each mode confidently.

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 coverage is 50%, and the schema already labels a, b, phrase, query, as_of and a_start with their owning op. The description's real contribution is giving meaning to the op enum values, which the schema lists without explanation. It does not clarify the a/b versus a_start/a_end distinction, anchor, lang, or limit.

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?

Names the resource (temporal reasoning) and enumerates four concrete operations — Allen interval relations, duration arithmetic, date normalization, historical recall — which is far more specific than a tautology. It loses a point because it never distinguishes itself from the sibling memory_eval_temporal, and the 'historical recall' / snapshot capability is described only in vague terms.

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

Usage Guidelines2/5

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

'Pass op=relation|duration_between|normalize|snapshot' tells the agent which values exist but not when to pick each one, what each returns, or when to prefer this tool over memory_eval_temporal or memory_episode_recall. There are no exclusions or prerequisites, so the agent must infer op selection from the schema alone.

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