draft_memory

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

The description discloses that the tool is non-destructive and does not commit to canonical memory, which aligns with the 'destructiveHint: false' annotation. It adds value by explaining the draft behavior, though it does not cover other behavioral aspects like auth or rate limits.

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 concise and well-structured: a one-line purpose, a bullet-like list of arguments with types/defaults, and a clear return statement. Every sentence adds value without redundancy.

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, combined with the output schema, provides sufficient information for most use cases. It covers the core purpose, parameters (mostly), and return format. The omission of 'branch_id' is a minor gap, but overall completeness is high.

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?

With 0% schema description coverage, the description compensates by detailing five of six parameters (observation, tags, importance, context, confidence) including types and defaults. However, 'branch_id' is missing from the description, leaving a gap.

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 clearly states the tool's purpose: 'Create a reviewable draft without writing to canonical memory.' It uses a specific verb ('create') and resource ('draft'), and distinguishes it from sibling tools like 'remember' that write to canonical memory.

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 provides clear context for when to use the tool ('without writing to canonical memory'), implying it's for proposing content for review before committing. However, it does not explicitly name alternative tools or provide 'when not to use' guidance.

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