Store content as a searchable memory with optional category and tags, enabling later retrieval using semantic, keyword, and tag-based search.
Write a new memory. Choose a category that fits the content.
| Name | Required | Description | Default |
|---|---|---|---|
| tags | No | Tags for organization | |
| content | Yes | The memory content | |
| category | No | Category (default: general) |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must disclose behavioral traits. It only states that it writes a memory, but does not mention side effects, return values, error behavior, or requirements. There is no indication of whether it overwrites existing memories or what happens on success, which is a significant gap for a write operation.
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?
The description is a single, concise sentence that avoids verbosity. However, it is so brief that it sacrifices substantive content. It earns points for efficiency but could be structured better by front-loading critical behavioral information.
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 simple tool with three parameters and no output schema, the description lacks essential context: no mention of what the tool returns, no indication of when to use it vs. update_memory, and no behavioral details. Given no annotations, this is incomplete and leaves the agent guessing about the tool's full effect.
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%, so the schema already documents all parameters. The description adds a small hint about category selection ('Choose a category that fits the content') but does not introduce new semantics beyond the schema. It meets the baseline for a well-covered schema.
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?
The description states 'Write a new memory' which clearly identifies the verb (write/create) and resource (memory). It is distinct from siblings like read_memories, update_memory, and delete_memory, leaving no ambiguity about what this tool does.
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?
The description offers no guidance on when to use this tool versus alternatives. It does not mention that this is for creating new memories, while update_memory handles modifications, or that search_memories is for retrieval. The phrase 'Choose a category' is about parameter selection, not usage context.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.