Skip to main content
Glama

search_decisions

Read-onlyIdempotent

Search past decisions using keyword matching to recall prior resolutions across sessions, roadmaps, and projects.

Instructions

Search past decisions across sessions and roadmap phases. Keyword search over an FTS5/BM25 index (Porter-stemmed) — NO semantic/vector matching, so recall depends on sharing keywords with the stored decision; for a concept with no shared words, browse list_decisions or list_tags instead. Default (E1): summary-first rows — {id, decision (one-line ≤140), file_path, do_not_revert, tags, score}, dropping per-row snippet/origin. Pass full=true for untruncated rows, expand(ids=[...]) to fetch specific decisions in full, or summary_only=true for a ~70%-smaller {id, summary, score} payload. Answers 'has anyone decided this before?'

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fullNoReturn untruncated decision text (default false)
limitNoMax results (default 5, max 20)
queryYesKeywords to search (e.g. 'threshold', 'uuid', 'retry')
session_idNoOptional — filter to a specific session
all_projectsNov3.6.0: search EVERY registered project's decisions, not just the current one. Each result gains `project` + `project_path`. Use to recall how you solved something in another repo. Default false.
summary_onlyNov2.1.2 Item 28: return id+summary+score only (smallest payload)
Behavior5/5

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

Adds substantial behavioral context beyond annotations: confirms the tool is a read-only, idempotent operation (consistent with annotations), details the indexing algorithm (FTS5/BM25, Porter-stemmed), specifies default response format (summary-first rows with specific fields), and describes optional output modes. No contradiction with annotations.

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

Conciseness5/5

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

Every sentence earns its place. The description is front-loaded with the main purpose, then covers indexing, output format, and parameter options without unnecessary words. Efficiently structured for an AI agent to quickly grasp key information.

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?

Given no output schema, the description adequately explains the return format (fields and structure). It covers all relevant behaviors, options, and usage context for a tool with 6 parameters and multiple output modes, making it a complete and useful reference.

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?

Despite 100% schema description coverage, the description adds meaningful context: explains default behavior for full and summary_only, the effect of all_projects (v3.6.0, adding project fields), and the structure of the default response. This enhances understanding beyond the schema alone, though the schema already provides good baseline.

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?

Clearly states the tool performs keyword search on past decisions using FTS5/BM25 with Porter stemming, explicitly distinguishing from semantic search and from browsing tools like list_decisions/list_tags. The verb 'search' plus the specific resource and scope makes it highly distinguishable from siblings.

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?

Provides explicit guidance on when to use this tool (searching for previous decisions with shared keywords) and when to use alternatives (browsing list_decisions or list_tags for concepts without shared words). Also explains default behavior and key parameters like full, expand, and summary_only.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/sachinshelke/codevira'

If you have feedback or need assistance with the MCP directory API, please join our Discord server