memory_key_facts_updateUpdate an existing key fact by its UUID to replace stored content with new text, keeping recalled session information accurate.
Update the content of an existing key fact by its ID.
| Name | Required | Description | Default |
|---|---|---|---|
| fact_id | Yes | UUID of the fact to update | |
| new_content | Yes | Replacement fact text |
Changes observed during successful MCP inspections.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=true, so the agent knows this is a destructive write. The description adds a little context by saying the fact must be 'existing' and that only content is replaced, but it does not disclose whether the old text is overwritten wholesale, whether the fact ID must belong to the caller, or error behavior on a bad ID.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One front-loaded sentence, zero padding, and the key mechanism (ID-based targeting) appears immediately. It is efficient, though its brevity contributes to the guidance gaps noted elsewhere.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a 2-parameter update with full schema coverage and annotations covering the safety profile, the essentials are present. What is missing is the surrounding context an agent needs to choose this over remember/forget and to know how a failed update behaves, which keeps it at minimum-viable rather than complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% (both fact_id and new_content are documented inline), so the schema carries parameter meaning. The description restates the same idea ('by its ID', 'content') without adding format, validation, or ID-sourcing detail, so baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb (Update), resource (key fact content), and mechanism (by its ID), so the action is unambiguous. However, it does nothing to distinguish itself from the sibling memory_key_facts_remember, which also writes facts, leaving the agent to guess which mutation path to take.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No when-to-use guidance at all: it never says to use this only for existing facts or that memory_key_facts_remember is the tool for creating new ones, nor what happens if fact_id does not resolve. For a mutating tool sitting alongside remember/forget/retrieve, that gap matters.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.