ToolForte

Remember a value

memory_set

DestructiveIdempotent

Store a value under a key so you can read it back in a LATER session. Use this to remember anything worth keeping: what you already processed, a running list, a decision, intermediate results. Without it, everything you learn is lost when this conversation ends. Requires a free API key (Authorization: Bearer tf_...) so entries stay private to you: https://toolforte.com/developers

Input Schema

TableJSON Schema

Name	Required	Description	Default
`key`	Yes	Identifier, may be namespaced like project/alpha/todo
`value`	Yes	Value to store as a string; serialise objects to JSON

Output Schema

TableJSON Schema

Name	Required	Description
`key`	No	The memory key
`bytes`	No	Size in bytes
`result`	No	The result, when it is not an object
`replaced`	No	Whether an earlier value under this key was overwritten

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed1 schema field changedSep 5, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "https://json-schema.org/draft/2020-12/schema",
+  "additionalProperties": {},
+  "properties": {
+    "bytes": {
+      "description": "Size in bytes",
+      "type": "number"
+    },
+    "key": {
+      "description": "The memory key",
+      "type": "string"
+    },
+    "replaced": {
+      "description": "Whether an earlier value under this key was overwritten",
+      "type": "boolean"
+    },
+    "result": {
+      "description": "The result, when it is not an object"
+    }
+  },
+  "type": "object"
+}

First observedSep 1, 2026

TDQS

A4.2/5.0

Behavior4/5

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

It discloses that the tool requires a free API key and that entries are private to the caller, which is useful operational context beyond the annotations. The annotation set already marks the operation as idempotent and destructive, so the description is not required to repeat overwrite semantics; it also adds the cross-session behavior. No contradiction with annotations.

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

Conciseness4/5

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

The description is short and front-loaded with the primary action and persistence guarantee. The 'Without it...' sentence is slightly motivational, but the overall length is still appropriate and every sentence adds either behavior or auth context.

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

Completeness5/5

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

For a simple two-parameter write tool with a full input schema and an output schema present, the description covers the key facts: what is stored, why to use it, how long it lasts, and the required authentication. The only notable omission is explicit overwrite behavior, but the destructiveHint annotation covers that signal.

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?

Input schema coverage is 100% and both parameters are described in the schema (key as identifier with namespacing, value as a JSON-serialised string). The description only restates 'under a key' without adding parameter details, so the schema is doing the work; baseline 3 applies.

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 states a specific verb and resource ('Store a value under a key') and adds the key behavior of cross-session persistence ('read it back in a LATER session'). It is clearly differentiated from sibling tools like memory_get, memory_delete, and memory_list by focusing on the write side of the memory API.

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?

It provides explicit use context: remember anything worth keeping, with concrete examples (processed items, running list, decision, intermediate results), and motivates persistent storage ('Without it, everything you learn is lost'). It does not explicitly list exclusions or contrast with memory_delete/list, but those are not competing operations for writing a value, so the guidance is sufficient.

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

All ToolForte tools Inspect

Try in Browser

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

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0

Disambiguation4/5

Most tools target a clearly distinct resource and action, so an agent can usually tell them apart. A few close pairs exist (generate_test_bsn vs generate_brp_test_data, html_to_pdf vs url_to_pdf, read_page vs url_screenshot), but the descriptions draw clear boundaries.

Naming Consistency4/5

Tool names consistently use snake_case and mostly follow a verb_noun pattern like generate_slug, validate_email, or pdf_merge. There are a few noun-style exceptions such as base64, csv_to_json, and password_strength, but no mixed casing or chaotic naming.

Tool Count3/5

40 tools is heavy and exceeds the comfortable selection range for most agents. The server presents itself as a general-purpose utility toolbox, so the breadth is defensible, but the large flat tool list creates real navigation burden.

Completeness4/5

The toolkit covers common encoding, conversion, image/PDF, validation, Dutch-specific test data, memory, and workflow needs quite well. Minor gaps like PDF text extraction or JSON-to-CSV conversion exist, but agents can typically work around them.

Resources

Need Help?