Skip to main content
Glama
Cloto-dev

CPersona

Official
by Cloto-dev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

get_session_findings

Read-only

Pull storage-integrity findings across the whole database on demand to audit memory health, then rerun each probe by its check name or cap results per kind.

Instructions

Pull the storage-integrity findings on demand (the SuperAuditor pull contract, docs/SUPERAUDITOR_STANDARD.md) instead of reading them off check_health: the same detector as check_health(fix=false) over the WHOLE database. Read-only, never repairs. Each finding carries kind (a check registry name, or an escalation tier this seam mints for a runner that grades its own severity, e.g. null_embedding_pipeline_down — a tier is NOT a registry name), check (the registry name that produced it: check_health(checks=[finding['check']]) re-runs exactly that probe) and a static per-kind severity (critical = the read contract is broken now / warn = two stored facts contradict / info = an observation). check_health's own verdict rides along as health_severity; a probe that raised is reported as kind check_crashed instead of failing the pull. NOT free: the registry runs unfiltered, including two whole-database reads (the FTS5 integrity-check over both indexes and PRAGMA quick_check), so every pull is O(database); budget it by call frequency. There is deliberately no cheap subset. Findings are NOT filtered by agent_id or project_id: slicing them by the caller's bucket would hide exactly the forgotten rows (scope a repair with check_health(agent_id=...)). Honest caps: findings holds at most per_kind_limit rows per kind, capped_kinds names every kind that had more, and total and the counts describe the RETURNED set only. summary restates it in prose (include_summary=false skips it). Without a session_key on a shared remote transport the response carries identity_shared: true; _meta.server_version identifies the running instance.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
session_keyNoOpaque client-declared session identity (partition hint, not authentication). Empty on a non-stdio transport marks the response identity_shared.
per_kind_limitNoMaximum findings returned per kind (default 5, minimum 1). Kinds that hit it are listed in capped_kinds.
include_summaryNoInclude the human-readable `summary` rendering (default true). It restates `findings` in prose — set false when machine-reading.

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. Addedv2.5.10

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only supply readOnlyHint=true, yet the description adds substantial behavior: never repairs, cost is O(database) with two named whole-database reads, findings are unfiltered by agent_id/project_id, hard caps with capped_kinds, and identity_shared on shared transports. This is far beyond what the annotation conveys.

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?

Core purpose and the read-only contract are front-loaded, and nearly every sentence carries load-bearing detail on return fields and cost. It is nonetheless dense and heavy on capitalized emphasis and parentheticals, so it is slightly longer than strictly necessary for a three-parameter tool.

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?

There is no output schema, so the description carries the full burden and does so: it defines kind, check, severity tiers, health_severity, the check_crashed case, findings, capped_kinds, total, summary, identity_shared and _meta.server_version. An agent has everything needed to interpret the return.

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 description coverage is 100%, so the schema already documents all three params, setting a baseline of 3. The description goes further by tying session_key empty-on-shared-transport to identity_shared, per_kind_limit to capped_kinds, and include_summary to prose output, adding real semantic context.

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?

States a specific verb and resource ('Pull the storage-integrity findings on demand') and immediately disambiguates from the sibling check_health, noting it is 'the same detector as check_health(fix=false) over the WHOLE database'. An agent can distinguish this from check_health without opening either schema.

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?

Explicitly routes usage: use this 'instead of reading them off check_health', but scope a repair with check_health(agent_id=...). It also gives a budgeting rule ('budget it by call frequency') and warns there is deliberately no cheap subset, covering when not to use it.

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