Skip to main content
Glama

sage_reflect

Store task reflections to improve future performance by recording what worked (dos) and what didn't (don'ts) after completing significant work.

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?

With no annotations provided, the description carries full burden. It clearly states this is a storage/write operation ('store them') and explains the learning benefit, but lacks details on persistence behavior (e.g., storage location, retrieval method, data format, or error handling). It doesn't mention authentication needs, rate limits, or side effects beyond storage.

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 appropriately sized and front-loaded with the core purpose. The research citation adds value but could be slightly more concise. All sentences contribute to understanding the tool's role and importance, with no wasted words.

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 write operation tool with 4 parameters and no annotations or output schema, the description adequately covers purpose and usage but lacks details on behavioral aspects like storage mechanics, error cases, or return values. It provides good motivation but incomplete operational context for an agent to use it confidently.

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

Parameters4/5

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

Schema description coverage is 100%, so the schema fully documents all 4 parameters. The description adds value by explaining the purpose of 'dos' and 'donts' parameters in the context of learning ('Both successes and failures make you better'), providing semantic context beyond the schema's technical descriptions. However, it doesn't add details for 'domain' or 'task_summary' parameters.

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 explicitly states the tool's purpose as 'End-of-task reflection' with specific verbs ('store what went right (dos) and what went wrong (don'ts)') and distinguishes it from siblings by focusing on feedback storage rather than other memory operations like listing or forgetting. It clearly defines the resource being managed (reflection data).

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

Usage Guidelines5/5

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

The description provides explicit guidance on when to use it ('Call this after completing a significant task') and why ('feedback loop is critical'), with research evidence to support its importance. It implicitly distinguishes from siblings by not being used for retrieval or other memory operations, though it doesn't name specific alternatives.

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/s-age'

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