How do I use SuperMemory MCP?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@SuperMemory MCP retrieve lessons for handling database connection timeouts" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

SuperMemory MCP

by YashvantHange

Overview Schema Related Servers Score Discussions

Python

Local

SuperMemory

MCP-first agent learning layer for Claude, Cursor, and custom agent workflows.

SuperMemory captures distilled lessons from failures and corrections — not full conversation transcripts — validates them before storage, and improves agents over time through a closed-loop cycle.

PyPI GitHub Release License: MIT MCP Registry

Quick start

pip install supermemory-agent
supermemory-agent --storage .supermemory --transport stdio

Or with uv:

uvx supermemory-agent --storage .supermemory --transport stdio

Latest release: v0.2.4 — wheel + sdist attached on every GitHub Release.

Related MCP server: memmd-mcp

What you get

Component	Description
MCP server	29 tools + 4 resources over stdio (or streamable HTTP)
Agent skill	`skills/supermemory-agent-learning/SKILL.md` — bundled in the PyPI package
Python SDK	In-process integration via `uall_python`
REST API	FastAPI server for remote / polyglot clients
Storage	Local `.supermemory/` files by default; SQLite and PostgreSQL optional

Everything lives in one repo: MCP server, skills, SDK, REST API, tests, and release packages.

Install

PyPI (recommended)

pip install supermemory-agent

After install, bundled skills are at site-packages/skills/supermemory-agent-learning/. Copy to your editor skills folder if needed.

GitHub Release (offline / pinned version)

Each release ships installable assets:

pip install https://github.com/YashvantHange/SuperMemory/releases/download/v0.2.4/supermemory_agent-0.2.4-py3-none-any.whl

Browse all versions: github.com/YashvantHange/SuperMemory/releases

From source (developers)

git clone https://github.com/YashvantHange/SuperMemory.git
cd SuperMemory
pip install -e ".[dev]"
python -m pytest tests/ -v

Configure MCP

Cursor

Copy examples/cursor.mcp.json to .cursor/mcp.json in your project:

{
  "mcpServers": {
    "supermemory": {
      "command": "supermemory-agent",
      "args": ["--storage", ".supermemory", "--transport", "stdio"]
    }
  }
}

Claude Desktop

Merge examples/claude_desktop_config.json into:

%APPDATA%\Claude\claude_desktop_config.json

Restart Claude Desktop after saving.

Run manually

Do not run supermemory-agent alone in a terminal — stdio mode expects JSON-RPC from an MCP client. Pressing Enter in the shell causes a JSON parse error.

# For local HTTP testing only:
supermemory-agent --transport streamable-http

When configured in Cursor or Claude Desktop, the client launches the server automatically over stdio.

Agent skills (Cursor + Claude Code)

Source	Path
Canonical (edit here)	`skills/supermemory-agent-learning/`
Cursor project	`.cursor/skills/supermemory-agent-learning/`
Claude Code project	`.claude/skills/supermemory-agent-learning/`
PyPI install	`site-packages/skills/supermemory-agent-learning/`

After editing skills/, sync copies:

python scripts/sync_skills.py

Mention SuperMemory, agent learning, or MCP memory in chat to load the skill.

Learning loop

retrieve → record_failure → reflect(event_ids) → validate → process_promotions
         → retrieve again → report_outcome

Core rule: capture workflow outcomes and distilled lessons only — never full transcripts. Default retrieval budget: max_tokens=800.

MCP tools (29)

Core (13): retrieve, record_event, record_failure, record_correction, reflect, validate, process_promotions, report_outcome, get_policies, add_policy, add_skill, search_skills, get_skill

Extended UALL (16): learn.run.start, learn.run.event, learn.run.end, learn.store, learn.retrieve, learn.reflect, learn.validate, learn.evaluate, learn.feedback, learn.improvements, learn.analytics, learn.policies, learn.experiment, learn.rollback, learn.skills, learn.telemetry

All tools include MCP safety annotations (readOnlyHint / destructiveHint).

MCP resources (4)

supermemory://policies/active
supermemory://lessons/{lesson_id}
supermemory://memory/{lesson_id}/provenance
supermemory://skills/{skill_id}

Python SDK

from uall_python import UALLClient

client = UALLClient(storage="file")

with client.run(workflow_id="pdf-pipeline", step="planner", namespace="team:eng") as run:
    lessons = run.retrieve(step="planner", max_tokens=800)
    run.record_failure(snippet="chose OCR for searchable PDF", tags=["routing"])
    run.report_lesson_outcome(lesson_id="lesson_001", used=True, accepted=True, improved=True)

REST API

python -m uall_server

Server: http://localhost:8000 — see api/openapi.yaml.

Storage

Tier	Backend	Config
Default	`.supermemory/` JSON files	`SUPERMEMORY_STORAGE_PATH` or `UALL_DATA_DIR`
Optional	SQLite	`UALL_STORAGE_BACKEND=sqlite`
Enterprise	PostgreSQL	`UALL_STORAGE_BACKEND=postgres`

Project layout

SuperMemory/
├── src/supermemory_mcp/          # MCP server (29 tools, 4 resources)
├── skills/supermemory-agent-learning/   # Agent skill (SKILL.md)
├── packages/uall/                # Core learning engine
├── packages/uall_python/         # Python SDK
├── packages/uall_server/         # REST API
├── examples/                     # Cursor + Claude Desktop MCP configs
├── tests/                        # 74 tests incl. stdio MCP transport
└── docs/                         # Publishing, releases, privacy

Tests

python -m pytest tests/ -v
python -m pytest tests/test_mcp_server.py -v   # real stdio MCP transport
python -m pytest tests/test_core.py -v         # closed-loop integration

Docs

Doc	Purpose
docs/GIT_SETUP.md	Fix commit author name/email on GitHub
docs/RELEASES.md	Release checklist — every tag ships wheel + sdist
docs/PUBLISHING.md	PyPI, MCP Registry, Cursor & Claude directories
PRIVACY.md	Privacy policy
skills/README.md	Agent skill install paths

MCP Registry name: io.github.YashvantHange/supermemory
PyPI package: supermemory-agent

License

MIT — see LICENSE

Available Tools

29 tools

add_policyC

Add a local policy rule.

ParametersJSON Schema

Name	Required	Default
`rule`	Yes
`priority`	No
`namespace`	No	global

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.4/5.0

Behavior2/5

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

Annotations indicate readOnlyHint=false and destructiveHint=false, so adding a policy is a non-destructive write. The description adds no behavioral context beyond this, such as side effects, required permissions, or whether changes are reversible.

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

Conciseness2/5

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

The description is extremely brief (one sentence), but it under-specifies the tool. It lacks important information that would need to be added, so it is not appropriately sized.

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?

Given the tool has 3 parameters (one required) and an output schema, the description fails to adequately cover usage context and parameter semantics. It is incomplete for an agent to use correctly.

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

Parameters1/5

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

Schema description coverage is 0%, so the description must explain parameters. It only says 'Add a local policy rule' with no details on the meaning of 'rule', 'priority', or 'namespace', their formats, or defaults.

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?

The description states 'Add a local policy rule,' which clearly identifies the action (add) and resource (policy rule). However, it does not differentiate from sibling tools like add_skill or get_policies, and the term 'local' is not explained.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, scenarios, or exclusions.

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

add_skillC

Add a reusable skill/workflow block.

ParametersJSON Schema

Name	Required	Default
`name`	Yes
`steps`	Yes
`tools`	No
`version`	No	0.1.0
`metadata`	No
`workflow`	No
`namespace`	No	global
`description`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.4/5.0

Behavior2/5

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

Annotations indicate readOnlyHint=false and destructiveHint=false, so the description needed to add behavioral context beyond that. However, the description merely repeats the creation intent without disclosing side effects, idempotency, permissions, or behavior on duplicates. The brief phrasing adds no meaningful transparency.

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

Conciseness2/5

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

The description is extremely concise—a single sentence—but sacrifices essential information. It fails to provide any structural details such as parameter context or usage notes, making it under-specified rather than efficiently concise. Every sentence should earn its place; here, the one sentence does not carry its weight.

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?

Given the tool's complexity (8 parameters, multiple optional fields) and the absence of parameter descriptions in the schema, the description is woefully incomplete. It does not explain the purpose of each field, required relationships (e.g., between steps and workflow), or typical usage patterns. The presence of an output schema reduces the need to explain returns, but input semantics remain unclear.

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

Parameters1/5

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

Schema description coverage is 0%, so the description must compensate by explaining parameter meanings and usage. The description does not mention any of the eight parameters (name, description, steps, tools, version, metadata, workflow, namespace). The agent has no clue what each parameter represents or how they interact, severely hindering correct invocation.

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?

The description states 'Add a reusable skill/workflow block,' which clearly indicates the verb (add) and the resource (skill/workflow block). It is specific enough to distinguish from simple actions like 'get' or 'delete,' but does not differentiate from sibling tools like 'add_policy' or 'learn.skills' that may involve similar concepts.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as 'add_policy', 'search_skills', or 'learn.skills'. There are no prerequisites, exclusions, or context criteria mentioned, leaving the agent to infer usage from the name alone.

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

get_policiesB

Read-only

Return active policies visible to a namespace.

ParametersJSON Schema

Name	Required	Description	Default
`namespace`	No		global

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

B3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description adds little beyond stating it returns 'active policies.' It does not explain what 'active' means or how namespace affects visibility, but the read-only nature is clear.

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?

The description is a single concise sentence, front-loading the key action and resource. No wasted words, though more detail could be added without harming conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one parameter and an output schema, the description is minimally adequate. However, it lacks details on filtering, ordering, or interpretation of 'active,' and fails to differentiate from similar sibling tools.

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

Parameters2/5

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

The schema has 0% description coverage for the only parameter 'namespace.' The description only mentions 'visible to a namespace' without specifying format, valid values, or behavior when omitted (default 'global'). It partially compensates but remains vague.

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?

The description clearly states the action ('Return') and resource ('active policies visible to a namespace'). It is specific about what the tool retrieves, but does not distinguish from sibling tools like search_skills or learn.policies.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It does not mention any prerequisites, limitations, or scenarios where another tool would be more appropriate.

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

get_skillA

Read-only

Read a reusable skill by ID.

ParametersJSON Schema

Name	Required	Description	Default
`skill_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

A3.9/5.0

Behavior3/5

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

Annotations already provide readOnlyHint=true and destructiveHint=false, which the description (saying 'Read') aligns with. The description adds minimal behavioral context beyond annotations, such as clarifying it's a 'reusable skill', but doesn't disclose additional traits like authorization needs or behavior on missing ID.

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?

The description is a single, front-loaded sentence with no unnecessary words. Every word ('Read', 'reusable skill', 'by ID') is essential and clear. It is appropriately minimal for a simple tool.

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?

Given the tool's simplicity (one required parameter) and the presence of an output schema (which documents return structure), the description is sufficient. It covers the core purpose and input. It could mention error handling or success behavior, but for a basic read operation, it is nearly complete.

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

Parameters2/5

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

With 0% schema description coverage, the description must compensate but only says 'by ID'. It does not explain the format, source, or constraints of the skill_id parameter. The schema's title 'Skill Id' provides some hint, but the description adds no meaningful semantic beyond stating the obvious.

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?

The description clearly states the action (Read) and the resource (reusable skill by ID). It distinguishes from siblings like search_skills (search vs. get by ID) and add_skill (add vs. get). The verb-resource pairing is specific and unambiguous.

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?

The description clearly indicates the tool is for reading a skill by its ID, implying use when the ID is known. However, it does not explicitly mention alternatives like search_skills for finding skills by other criteria, nor does it state when not to use it. The context is clear but lacks exclusions.

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

learn.analyticsD

Read-only

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.evaluateD

Read-only

ParametersJSON Schema

Name	Required	Description	Default
`run_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.experimentD

ParametersJSON Schema

Name	Required	Description	Default
`variant_b`	Yes
`resource_id`	Yes
`traffic_split`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.feedbackD

ParametersJSON Schema

Name	Required	Description	Default
`rating`	Yes
`run_id`	No
`comment`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.improvementsD

Read-only

ParametersJSON Schema

Name	Required	Description	Default
`agent_id`	No
`workflow_id`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.policiesD

Read-only

ParametersJSON Schema

Name	Required	Description	Default
No parameters

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.reflectD

ParametersJSON Schema

Name	Required	Description	Default
`fix`	No
`step`	No
`failure`	No
`workflow`	No
`event_ids`	No
`root_cause`	No
`suggestion`	No
`auto_promote`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.retrieveD

Read-only

ParametersJSON Schema

Name	Required	Description	Default
`step`	No
`query`	Yes
`workflow`	No
`namespace`	No
`max_tokens`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.rollbackD

Destructive

ParametersJSON Schema

Name	Required	Description	Default
`resource_id`	Yes
`resource_type`	Yes
`target_version`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.run.endD

ParametersJSON Schema

Name	Required	Description	Default
`run_id`	Yes
`success`	Yes
`lessons_used`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.run.eventD

ParametersJSON Schema

Name	Required	Description	Default
`step`	No
`tags`	No
`after`	No
`agent`	No
`before`	No
`intent`	No
`run_id`	Yes
`snippet`	No
`workflow`	No
`event_type`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.run.startD

ParametersJSON Schema

Name	Required	Description	Default
`step`	No
`agent`	No
`agents`	No
`namespace`	No
`workflow_id`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.skillsD

Read-only

ParametersJSON Schema

Name	Required	Description	Default
`query`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.storeD

ParametersJSON Schema

Name	Required	Description	Default
`lesson_json`	Yes

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.telemetryD

ParametersJSON Schema

Name	Required	Description	Default
`used`	No
`run_id`	No
`accepted`	No
`improved`	No
`lesson_id`	Yes
`telemetry_id`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

learn.validateD

ParametersJSON Schema

Name	Required	Description	Default
`fix`	Yes
`failure`	Yes
`event_ids`	No
`root_cause`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1/5.0

Behavior1/5

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

Tool has no description.

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

Conciseness1/5

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

Tool has no description.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has no description.

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

Parameters1/5

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

Tool has no description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

Tool has no description.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tool has no description.

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

process_promotionsC

Process pending validated lessons and promote passing items.

ParametersJSON Schema

Name	Required	Description	Default
`limit`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.9/5.0

Behavior3/5

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

Annotations indicate a mutation (readOnlyHint=false) that is not destructive (destructiveHint=false). The description adds that it promotes items, aligning with the annotation. However, it does not elaborate on side effects or permissions beyond the annotation's minimal disclosure.

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?

The description is a single concise sentence with no redundancy. It efficiently conveys the core action without wasted words, appropriate for a simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no required fields, output schema present), the description covers the main functionality. However, the lack of parameter documentation reduces completeness for effective use.

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

Parameters1/5

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

The single parameter 'limit' has no description in the schema (0% coverage), and the tool description does not mention it. The agent must guess its purpose (e.g., max number of items to process), which is a significant gap.

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?

The description clearly states it processes pending validated lessons and promotes passing items, specifying the action and resource. It distinguishes from sibling tools like validate, which would be a prerequisite step.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives like validate or other tools. The context 'pending validated lessons' implies a sequence, but no exclusions or conditions are given.

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

record_correctionD

Record a bounded correction signal.

ParametersJSON Schema

Name	Required	Default
`step`	No
`tool`	No
`agent`	No
`domain`	No
`payload`	No
`summary`	Yes
`language`	No
`workflow`	No
`namespace`	No	global
`environment`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

D1.5/5.0

Behavior2/5

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

Annotations already indicate readOnlyHint=false (modifies) and destructiveHint=false. The description adds no behavioral context beyond this, such as side effects, validation rules, or the meaning of 'bounded' in terms of system state.

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

Conciseness1/5

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

While concise, the description is severely under-specified for a 10-parameter tool. It sacrifices necessary detail for brevity, making it unhelpful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema and many siblings, the description provides no completeness. It does not explain what the tool returns, how it interacts with other tools, or how to use its parameters effectively.

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

Parameters1/5

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

Schema description coverage is 0%. The description mentions none of the 10 parameters, not even the required 'summary'. It fails to add any meaning beyond the schema's property names and types.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description provides a verb ('Record') and resource ('correction signal'), but 'bounded correction signal' is vague jargon. It does not clearly distinguish from siblings like 'record_failure' or 'learn.feedback', leaving the tool's exact purpose unclear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines1/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives. The description lacks any context about prerequisites, appropriate situations, or relationships to other tools.

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

record_eventB

Record a bounded significant event. Full transcripts should not be sent here.

ParametersJSON Schema

Name	Required	Default
`step`	No
`tool`	No
`agent`	No
`domain`	No
`payload`	No
`summary`	Yes
`language`	No
`workflow`	No
`namespace`	No	global
`event_type`	Yes
`environment`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

B3.1/5.0

Behavior3/5

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

Annotations already indicate write behavior (readOnlyHint=false) and non-destructive (destructiveHint=false). The description adds little beyond 'bounded' and 'significant,' which are qualitative and do not disclose concrete behavioral traits like side effects or persistence.

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?

Two concise sentences with no redundancy. Front-loaded with purpose, followed immediately by a key usage guideline. Every word earns its place.

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?

Given 11 parameters, many siblings, and no output schema context in description, this is insufficient. It does not explain what constitutes a 'bounded significant event,' valid event types, or how the tool integrates with other tools. The description is too brief to be complete.

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

Parameters1/5

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

Schema description coverage is 0%, so the description must compensate for parameter meaning. It provides no information about any of the 11 parameters, including required ones like event_type and summary, making it impossible for an agent to know how to fill them.

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?

The description clearly states the tool records a bounded significant event, with the verb 'record' and object 'event'. It also hints at scope by excluding full transcripts, but does not differentiate from sibling tools like record_correction or record_failure.

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 description provides a negative guideline ('Full transcripts should not be sent here'), suggesting it's for summaries, but lacks explicit when-to-use vs alternatives or context for when to use this tool over siblings.

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

record_failureC

Record a bounded failure signal.

ParametersJSON Schema

Name	Required	Default
`step`	No
`tool`	No
`agent`	No
`domain`	No
`payload`	No
`summary`	Yes
`language`	No
`workflow`	No
`namespace`	No	global
`environment`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.4/5.0

Behavior2/5

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

Annotations indicate readOnlyHint=false and destructiveHint=false. Description adds no additional behavioral context such as side effects, permissions, or what 'bounded' means. Minimal transparency beyond annotations.

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

Conciseness2/5

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

Extremely short (5 words) but under-specified for a tool with 10 parameters. Lacks structure and essential information; conciseness is not achieved without adequate content.

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?

Given the tool complexity (10 params, annotations present, output schema exists), the description is insufficient to understand proper usage. It does not cover the meaning of 'bounded' or how to use parameters effectively.

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

Parameters1/5

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

Schema has 10 parameters with 0% description coverage. The description does not explain any parameter meaning, including required fields like 'summary' or optional ones like 'step', 'tool', 'payload', etc. No added value beyond the schema.

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?

Description states 'Record a bounded failure signal', which is a specific verb and resource. It distinguishes from sibling tools like record_correction and record_event. However, 'bounded' is ambiguous and not explained.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives like record_correction or record_event. No when-not-to-use or context provided.

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

reflectC

Create a candidate lesson from evidence events.

ParametersJSON Schema

Name	Required	Description	Default
`event_ids`	Yes
`suggestion`	No
`lesson_text`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.6/5.0

Behavior2/5

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

Annotations declare readOnlyHint=false and destructiveHint=false, but the description adds no additional behavioral context. It does not explain what 'candidate' means, whether events are consumed or preserved, what side effects occur, or if the operation is reversible. The description fails to add value beyond the annotations.

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?

The description is a single concise sentence that front-loads the main action. It is efficient with no wasted words, but could benefit from additional structure or bullet points for clarity.

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?

Given the tool has 3 parameters (1 required), an output schema, and is a write operation, the description is incomplete. It does not describe the return value, clarify the nature of 'candidate lesson', or provide enough context for the agent to use the tool confidently. The presence of an output schema reduces the burden slightly but not enough.

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

Parameters1/5

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

The input schema has 0% description coverage for parameters, yet the description does not explain the purpose or behavior of any parameter (event_ids, suggestion, lesson_text). The agent receives no guidance on how these parameters influence the lesson creation, which is critical for correct invocation.

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?

The description 'Create a candidate lesson from evidence events' clearly uses a verb ('Create') and resource ('candidate lesson') and specifies the source ('evidence events'). However, it does not differentiate from the sibling tool 'learn.reflect' or other learning tools like 'learn.feedback', which limits its distinctiveness.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like 'learn.evaluate' or 'learn.improvements'. There are no explicit when-to-use or when-not-to-use conditions, leaving the agent without contextual decision support.

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

report_outcomeC

Report telemetry for a retrieved lesson.

ParametersJSON Schema

Name	Required	Description	Default
`used`	Yes
`run_id`	No
`accepted`	Yes
`improved`	Yes
`lesson_id`	Yes
`retrieval_id`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.4/5.0

Behavior2/5

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

Annotations state readOnlyHint=false and destructiveHint=false, which are consistent with a write operation. The description does not add any behavioral details beyond annotations, such as side effects, required permissions, or idempotency.

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

Conciseness3/5

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

The description is a single sentence, which is concise but lacks structure. It does not earn its place because it fails to provide essential parameter details.

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?

Given the tool's complexity (6 parameters, 4 required) and lack of parameter coverage, the description is incomplete. It does not explain what telemetry is reported, whether the operation is idempotent, or error conditions. The presence of an output schema does not compensate for missing parameter semantics.

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

Parameters1/5

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

Schema description coverage is 0%, and the description does not explain any parameters. The meaning of 'used', 'accepted', 'improved', 'run_id', 'retrieval_id' is not clarified, leaving the agent without sufficient guidance to populate them correctly.

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?

The description clearly states the verb 'report telemetry' and the resource 'retrieved lesson', which distinguishes it from sibling tools like record_event or record_failure. However, 'telemetry' is somewhat generic and could be more specific.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives such as record_event or learn.telemetry. No exclusions or context provided.

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

retrieveC

Read-only

Retrieve policy-first, stage-aware lessons.

ParametersJSON Schema

Name	Required	Default
`step`	No
`tool`	No
`agent`	No
`query`	Yes
`top_k`	No
`domain`	No
`language`	No
`workflow`	No
`namespace`	No	global
`max_tokens`	No
`environment`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is clear. The description adds no additional behavioral traits, such as failure modes or edge cases. Baseline score is appropriate given that annotations fulfill the basic need.

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

Conciseness2/5

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

At only six words, the description is extremely terse. True conciseness would include essential details, but here it omits critical context, making it under-specified rather than efficiently compact.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness1/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 11 parameters, no parameter descriptions, a complex sibling suite, and an output schema, the description is grossly incomplete. It fails to explain what constitutes 'lessons', the meaning of 'policy-first' and 'stage-aware', or what the tool returns. This is entirely inadequate for the tool's complexity.

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

Parameters1/5

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

The description provides no information about any of the 11 parameters, and the schema has 0% description coverage. The agent has no guidance on what parameters like 'step', 'domain', 'namespace', or 'max_tokens' mean or how to use them, severely hampering correct invocation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose3/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Retrieve policy-first, stage-aware lessons' identifies the action (retrieve) and resource (lessons), but the qualifiers 'policy-first' and 'stage-aware' are jargon and not explained. It lacks differentiation from the similar sibling 'learn.retrieve', leaving ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No usage guidance is provided. There is no indication of when to use this tool versus alternatives, nor any conditions or prerequisites mentioned. The description is purely functional without context.

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

search_skillsC

Read-only

Search reusable skills visible to a namespace.

ParametersJSON Schema

Name	Required	Default
`query`	Yes
`top_k`	No
`workflow`	No
`namespace`	No	global

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the description's mention of 'visible to a namespace' adds minimal behavioral insight beyond what is already available.

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?

The description is a single concise sentence, front-loading the core action. However, it could benefit from additional context without becoming verbose.

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?

Given the number of parameters and lack of schema descriptions, the description is incomplete. It does not explain search behavior or parameter usage, relying entirely on structured fields.

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

Parameters1/5

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

With 0% schema description coverage, the description fails to explain any of the four parameters (query, top_k, workflow, namespace). The only hint is 'namespace' in the description, leaving the agent with no understanding of required inputs.

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?

The description clearly states the tool searches for reusable skills within a namespace, using a specific verb and resource. However, it does not explicitly differentiate from sibling tools like 'get_skill' or 'retrieve'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description lacks context about prerequisites or conditions for use.

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

validateC

Validate a lesson candidate and enqueue approved lessons for promotion.

ParametersJSON Schema

Name	Required	Description	Default
`metadata`	No
`event_ids`	No
`reflection_id`	No
`candidate_lesson`	No

Output Schema

ParametersJSON Schema

Name	Required	Description
No output parameters

TDQS

C2.7/5.0

Behavior3/5

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

Annotations indicate non-readOnly and non-destructive, so tool is not pure read but not destructive. Description adds 'enqueue for promotion', implying a queuing side effect, but lacks details on permissions, rejection handling, or impact on other tools.

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 sentence with no wasted words. Could benefit from slight restructuring to highlight key actions, but remains appropriately concise.

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?

Output schema exists so return values are covered, but description leaves crucial gaps: no explanation of validation criteria, approval process, or parameter meanings. Given 4 unannotated parameters, the description is incomplete.

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

Parameters1/5

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

Schema description coverage is 0%, and description provides no explanation for any of the 4 parameters (metadata, event_ids, reflection_id, candidate_lesson). Description must compensate for missing schema details but fails entirely.

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?

Description clearly states verb 'validate and enqueue' and resource 'lesson candidate' for promotion. However, it lacks differentiation from sibling tools like learn.validate or process_promotions, which may have overlapping purposes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. Does not specify prerequisites, exclusions, or context in which validation is appropriate.

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

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

29 tool updatesv0.2.5Jun 27, 2026
- First observedadd_policy
- First observedadd_skill
- First observedget_policies
- First observedget_skill
- First observedlearn.analytics
- First observedlearn.evaluate
- First observedlearn.experiment
- First observedlearn.feedback
- First observedlearn.improvements
- First observedlearn.policies
- First observedlearn.reflect
- First observedlearn.retrieve
- First observedlearn.rollback
- First observedlearn.run.end
- First observedlearn.run.event
- First observedlearn.run.start
- First observedlearn.skills
- First observedlearn.store
- First observedlearn.telemetry
- First observedlearn.validate
- First observedprocess_promotions
- First observedrecord_correction
- First observedrecord_event
- First observedrecord_failure
- First observedreflect
- First observedreport_outcome
- First observedretrieve
- First observedsearch_skills
- First observedvalidate

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

D1.7/5.0

Disambiguation2/5

Many tools have overlapping or ambiguous names, especially the 'learn.*' tools with empty descriptions (e.g., learn.analytics, learn.evaluate) which are indistinguishable from each other. Additionally, 'retrieve' and 'learn.retrieve' appear to serve similar purposes, causing confusion.

Naming Consistency2/5

Naming conventions are mixed: some use underscore (add_policy), some use dot notation (learn.analytics), and some are single words (reflect). The 'learn.' prefix is applied inconsistently across tools, and verb_noun patterns are not uniformly followed.

Tool Count2/5

29 tools is excessive for a server that appears to manage policies, skills, and lessons. Many tools seem redundant (e.g., multiple learn.* tools) and could be consolidated. The scope does not justify this many distinct operations.

Completeness3/5

Core functionalities like adding, retrieving, and validating are present, but there are missing operations such as updating or deleting policies/skills. The learn.* tools are undocumented, leaving potential gaps in the learning pipeline unaddressed.

Maintenance

ActivityStale

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

memory
com.lodekeep
Portable memory for AI agents: capture once, recall across Claude, Cursor, and any MCP client.
Knowledge & Memory File Systems
1
Mnemoverse MemoryOAuth
io.github.mnemoverse
Hosted memory for AI agents that learns from outcomes — one key across Claude, Cursor & ChatGPT.
Knowledge & Memory Autonomous Agents
221
mifactory-agent-memory C
io.github.mifactory-bot
Persistent memory for AI agents across Claude, ChatGPT and any MCP client.
Knowledge & Memory Autonomous Agents Agent Orchestration
22
MemoryRouter A
ai.memoryrouter
Persistent AI memory shared across Claude, ChatGPT, coding agents, and compatible MCP clients.
Knowledge & Memory Search
101

Related MCP Servers

Agent Memory Bridge
Knowledge & Memory Developer Tools
zzhang82
A
license
A
quality
A
maintenance
MCP-native, local-first memory for coding agents that turns real sessions into reusable decisions, gotchas, and domain knowledge.
Updated 6 days ago (2026-08-31 00:17 UTC)
17
6
MIT
memmd-mcp
Knowledge & Memory Developer Tools
matamong
A
license
B
quality
D
maintenance
A shared memory layer for AI agents — one memory.md synced across Claude Desktop, Cursor, Claude Code, OpenAI Codex, and any MCP client.
Updated 6 months ago (2026-02-28 18:03 UTC)
4
2
MIT
Mnemoverse Memory
Knowledge & Memory Search
mnemoverse
A
license
A
quality
A
maintenance
Persistent long-term memory for AI agents — semantic recall across Claude, Cursor, ChatGPT & MCP.
Updated 3 days ago (2026-09-03 12:12 UTC)
10
519
21
MIT
total-agent-memory
Knowledge & Memory Coding Agents
vbcherepanov
A
license
Not graded
quality
A
maintenance
Persistent, local memory for AI coding agents that learns how you work, not just what you said. Supports Claude Code, Codex CLI, Cursor, and any MCP client.
Updated 10 days ago (2026-08-27 16:44 UTC)
66
MIT

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

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/YashvantHange/SuperMemory'

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