create_memory

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

With no annotations, the description carries the behavioral burden. It discloses the failure mode ('Errors if the target file already exists'), states that notes are 'untrusted inert history,' and implies unsupported agents will fail. It does not mention return values or permissions, but it provides meaningful behavioral detail for a write tool.

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?

Three short sentences with the core action front-loaded and no filler. The compatibility caveat and error behavior are compact and placed where they add value.

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?

The description covers the core write action, supported targets, and the no-overwrite error, making the tool callable. However, with five parameters, no output schema, and no annotations, the unexplained 'project' parameter and absent return-value context leave meaningful gaps.

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 coverage is only 60%, and the description adds almost no parameter-level meaning beyond the schema. The 'project' parameter is entirely unexplained, and 'content' is only implied. The agent values are mentioned in the prose, but cwd, file, and project semantics are not enriched.

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 opens with a specific verb and resource: 'Write a note into Claude, Codex, or Grok first-party memory markdown.' It clearly distinguishes this from sibling tools like put_note or read_memory by scoping to first-party memory and by listing unsupported agents.

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?

It gives an explicit exclusion ('Cursor, OpenCode, Gemini, and Copilot have no first-party memory store') and frames the intended use case as writing to first-party memory. It does not name a sibling alternative or specify when put_note would be preferred, so it stops short of full routing guidance.

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