Skip to main content
Glama

oc_skill_recall

Read-onlyIdempotent

Retrieve recency-sorted skills for a domain from the skill memory store. Optionally filter by contract ID and limit results for efficient recall.

Instructions

Retrieve skills from the JSON skill memory store for a given domain. Returns a recency-sorted list (last_used_at desc). Optionally filter by contract_id and cap results with limit (default 20). No LLM ranking — deterministic store order is returned as-is unless task/query or ranked is supplied. Each result carries codegenReplay ({available, artifacts}) for the LLM-free replay fast path. Use oc_skill_record to write skills.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
domainYesDomain to retrieve skills for (e.g. "amazon.com"). Must be a non-empty string ≤ 253 chars and match the domain used at record time.
contract_idNoOptional. Restrict results to skills whose contract_id matches this value exactly. Omit to return skills across all contracts.
taskNoOptional task text. When present, recall is ranked by deterministic task relevance.
queryNoOptional alias for task. Ignored when task is also provided.
rankedNoOpt in to deterministic ranked recall. Also enabled when task is provided.
limitNoMaximum number of skills to return. Default 20. Pass 0 to return an empty list. Values below 0 are treated as 0.
include_unpromotedNoWhen true, also surface promotionState=recorded skills. Default false: once a domain has any re_verified/recallable skill, recall hides recorded ones to keep the LLM-free fast path safe. Domains with no promoted skill auto-fallback to v1.x (all non-quarantined surface). (#1431)
include_quarantinedNoWhen true, also surface promotionState=quarantined skills. Default false; diagnostic only — they failed re-verification and should not be replayed. Independent of the recorded/promoted filter, so on an unpromoted domain (v1.x auto-fallback) it yields recorded + quarantined. (#1431)
use_run_statsNoOpt in to factor audit-log run statistics (recent-window failure rate) into ranked recall, demoting skills that fail often. Implies ranked recall. Default false (no audit-log I/O when off). When on, does a one-time synchronous audit-log scan per call. (#1457)
Behavior5/5

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

Annotations declare readOnlyHint, destructiveHint, idempotentHint, openWorldHint. Description adds recency-sorted order, codegenReplay fast path, deterministic ranking behavior, and detailed boolean parameter effects (include_unpromoted, include_quarantined, use_run_stats). No contradiction.

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?

Single paragraph with each sentence adding value. Could be more structured (e.g., bullet points for parameters), but remains concise and front-loads 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?

Covers return format, pagination via limit, ranking options, edge cases (limit 0/negative, unpromoted domains, audit-log stats). No output schema, but description compensates with behavioral details.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

100% schema coverage, description adds constraints (domain length, contract_id exact match), explains interaction between task/query/ranked, limit=0 behavior, and details on boolean parameters (e.g., unpromoted domain fallback). Adds significant value beyond schema.

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 retrieves skills from a JSON skill memory store for a given domain. Specifies verb 'retrieve' and resource 'skills', and distinguishes from sibling oc_skill_record (write).

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?

Provides guidance on default recency-sorted order, optional filters (contract_id, limit), and ranked recall via task/query or ranked. Mentions alternative oc_skill_record for writing. Could be more explicit about when to use vs other tools, but sufficient.

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/shaun0927/openchrome'

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