Store a project memory for coding agents, merging, superseding, or inserting it based on similarity to existing entries in cc-memory.
Add a memory via the anti-patch upsert path (merge / supersede / insert depending on similarity to existing).
| Name | Required | Description | Default |
|---|---|---|---|
| topic | No | ||
| content | Yes | Memory text, at least 10 characters after trimming (shorter content is dropped by the writer, not stored) | |
| project | No | ||
| category | Yes | ||
| importance | Yes |
Changes observed during successful MCP inspections.
v2.18.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It usefully discloses the non-obvious upsert behavior — merge, supersede, or insert based on similarity — which materially changes how an agent should think about writes. But it omits what 'supersede' does to the prior memory, whether content can be lost, and any auth or rate-limit context.
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?
A single front-loaded sentence with no filler; the core upsert behavior leads. The only drag is the opaque 'anti-patch' phrase, which costs a bit of clarity without adding length.
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 mutation tool with no annotations, no output schema, and 20% parameter coverage, the description is too thin. It never says whether the call returns an identifier, whether a merge preserves the old record, or what the required category/importance values mean in 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 only 20% (only 'content' is documented), so the description needed to compensate and does not. It says nothing about category, importance, topic, or project, leaving four of five parameters semantically unexplained.
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 (add) and resource (memory) and further specifies it is an upsert, which sharply separates it from read-oriented siblings like memory_search and memory_get_details. However, 'anti-patch upsert path' is internal jargon that an agent must reverse-engineer rather than a plain-language statement of what the 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?
There is no explicit when-to-use, when-not-to-use, or named alternative. An agent can infer this is the write path for memories, but nothing tells it when to prefer memory_add over, say, letting an existing memory be updated by search, or how it interacts with the other write-capable siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.