Skip to main content
Glama
po4erk91

Thread Keeper

by po4erk91
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

dialog_search

Read-only

Search ingested Claude Code transcripts using hybrid, semantic, or keyword FTS5 modes to retrieve relevant past dialogs by query, role, and project scope.

Instructions

Search ingested Claude Code transcripts.

mode='hybrid' (default) combines semantic and FTS5 keyword via RRF. mode='semantic' is pure cosine. mode='fts' is pure FTS5 keyword.

Input Schema

NameRequiredDescriptionDefault
kNo
modeNohybrid
roleNo
queryYes
cross_projectNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.19.1
    • addedInput schema / properties / cross_project
      Added value: +{
+  "default": false,
+  "title": "Cross Project",
+  "type": "boolean"
+}
  2. First observedv0.13.2

TDQS

B3.3/5.0
Behavior3/5

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

readOnlyHint=true already declares the safety profile, so the bar is lower. The description adds that only *ingested* transcripts are searchable, which is useful scope context, but says nothing about result limits, pagination, or whether the default scope is the current project versus all projects.

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?

Four short lines, purpose front-loaded, mode semantics tightly packed with no filler. The only cost is that the brevity is achieved by omitting parameters that needed explanation.

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?

With 5 parameters, 0% schema description coverage, and no output-schema relief for inputs, the description only covers one parameter. An agent cannot correctly set 'k', 'role', or 'cross_project' from this definition alone.

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 0% and there are no enums, so the schema gives the agent nothing. The description fully compensates for 'mode' by defining all three strategies, but 'k', 'role', and 'cross_project' are left completely undocumented despite being non-obvious.

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 and a specific corpus: 'Search ingested Claude Code transcripts.' That is far more precise than the generic sibling 'search', though it never explicitly says how it differs from that sibling, so an agent still has to guess between the two.

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 mode breakdown implies when each retrieval strategy is appropriate (hybrid as the default, semantic for conceptual similarity, fts for exact keyword hits), which is genuine guidance. But there is no explicit when-to-use versus alternatives such as 'search', 'extract_recent', or 'verbatim_user', and no exclusions or prerequisites.

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