Skip to main content
Glama
Cloto-dev

CPersona

Official
by Cloto-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

deep_check

Analyze stored agent memory for quality issues like anonymous sources, short content, stale profiles, orphaned episodes, and near-duplicates; optionally repair anonymous sources and short content.

Instructions

Deep heuristic analysis of memory data quality. Detects issues requiring recovery or judgment (anonymous sources, short/trivial content, stale profiles, orphaned episodes, stale threshold calibration, embedding-space near-duplicate pairs as merge candidates). fix=true applies repairs for: anonymous_source, short_content. Report-only (fix is accepted and ignored): stale_profile, orphaned_episodes, calibration_staleness, near_duplicate, unnormalized_content, embedding_norm — apply those decisions via merge_memories / delete_memory / calibrate_threshold / update_profile. Use checks parameter to select specific checks.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fixNoApply repairs (default: dry-run preview only)
checksNoChecks to run (empty = all). Options: anonymous_source, short_content, stale_profile, orphaned_episodes, calibration_staleness, near_duplicate, unnormalized_content, embedding_norm
agent_idYesAgent ID to check (required)
session_keyNoOpaque session identity you declare: a partition hint, not authentication and not a data filter. Selects which no-persist pause applies to this call. Omit to share one bucket with every caller that omits it. Full text on recall.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.6.1
    • addedInput schema / properties / session_key / maxLength
      Added value: +256
  2. Changed1 schema field changedv2.5.12
    • changedInput schema / properties / checks / description
      Previous value: -"Checks to run (empty = all). Options: anonymous_source, short_content, stale_profile, orphaned_episodes, calibration_staleness, near_duplicate"New value: +"Checks to run (empty = all). Options: anonymous_source, short_content, stale_profile, orphaned_episodes, calibration_staleness, near_duplicate, unnormalized_content, embedding_norm"
  3. Changed1 schema field changedv2.5.10
    • addedInput schema / properties / session_key
      Added value: +{
+  "default": "",
+  "description": "Opaque session identity you declare: a partition hint, not authentication and not a data filter. Selects which no-persist pause applies to this call. Omit to share one bucket with every caller that omits it. Full text on recall.",
+  "type": "string"
+}
  4. Changed1 schema field changedv2.4.37
    • changedInput schema / properties / checks / description
      Previous value: -"Checks to run (empty = all). Options: anonymous_source, short_content, stale_profile, orphaned_episodes"New value: +"Checks to run (empty = all). Options: anonymous_source, short_content, stale_profile, orphaned_episodes, calibration_staleness, near_duplicate"
  5. Addedv2.4.10

TDQS

A4.2/5.0
Behavior5/5

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

Goes well past the readOnlyHint=false annotation by disclosing the exact mutation semantics: fix defaults to dry-run preview, and fix=true only affects two of the eight checks while the rest ignore it. This partial-write behavior is the single most important thing an agent must know before setting fix=true and it is stated plainly.

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?

Front-loaded with the core purpose, then a parenthetical inventory of issue types, then the fix/report-only split, then follow-up tools. Dense but every clause carries information; the parenthetical enumeration pushes it toward a run-on sentence.

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 a four-parameter tool with no output schema, the description covers what it detects, what it mutates, what it ignores, and where to route unresolved issues. The main omission is any indication of the report shape or findings structure an agent should expect back.

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 baseline is 3 and the schema already documents fix, checks options, and session_key. The description still adds real meaning by mapping checks to their fix behavior and clarifying that an empty checks list runs everything. It does not, however, expand on the unusual session_key partitioning hint beyond what the schema says.

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?

Specific verb+resource: 'Deep heuristic analysis of memory data quality' with an enumerated set of detected issue classes (anonymous sources, stale profiles, orphaned episodes, near-duplicate pairs). An agent immediately knows this is a diagnostics/repair pass. It never explicitly contrasts itself with the sibling check_health, so sibling differentiation is only implicit via the check list.

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?

Strong routing guidance: it states which checks are auto-repairable (anonymous_source, short_content) and, for each report-only check, names the sibling to apply the decision (merge_memories / delete_memory / calibrate_threshold / update_profile). No explicit 'when to call this vs check_health' statement, so it stops short of a 5.

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