Skip to main content
Glama

sage_reflect

Record what went right and wrong after completing a task to learn from successes and failures, enabling continuous improvement through stored feedback.

Instructions

End-of-task reflection. Call this after completing a significant task to store what went right (dos) and what went wrong (don'ts). This feedback loop is critical — Paper 4 proved that agents with memory achieve Spearman rho=0.716 improvement over time while memoryless agents show rho=0.040 (no learning). Both successes and failures make you better. Store them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
domainNoKnowledge domain (e.g. debugging, architecture, user-prefs)general
dontsNoWhat went wrong — mistakes made, approaches that failed, things to avoid
dosNoWhat went right — approaches that worked, patterns to repeat
task_summaryYesBrief description of what the task was
Behavior3/5

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

No annotations exist, so the description must carry the full burden. It explains that the tool stores dos/don'ts for a feedback loop and references research on memory improvement, but does not disclose specific behavioral traits such as side effects, idempotency, or auth requirements.

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 relatively concise and front-loaded with the core purpose. The inclusion of research results (Paper 4) adds length but may be unnecessary for tool invocation. Overall, it is well-structured for its length.

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 has 4 parameters, no output schema, and no annotations, the description provides a clear purpose and usage context. It lacks some behavioral detail but is complete enough for a straightforward storage action.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description briefly mentions storing 'dos' and 'don'ts' and a 'task summary', but adds no additional meaning beyond what the schema descriptions already provide. Domain parameter is not elaborated.

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 identifies the tool as 'End-of-task reflection' for storing dos and don'ts. It uses a specific verb ('reflect') and resource ('task outcomes'), but does not explicitly contrast with sibling tools like sage_remember, which also stores information.

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 explicitly states when to call the tool: 'after completing a significant task'. It provides clear context but lacks explicit when-not-to-use instructions or references to alternative tools.

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/l33tdawg/sage'

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