Remember

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

No annotations are provided, so the description carries the full burden of behavioral disclosure — and it excels. It reveals three critical behaviors: no automatic overwriting, a conflict-return contract requiring caller judgment, and idempotent behavior for identical content. These are exactly the traits an agent needs to know before calling.

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 sentence that is informative and front-loaded with the core purpose, but it packs several concepts (conflict material, judgment options, idempotency, no-overwrite guarantee) into em-dash clauses. A structured list would improve scanability without lengthening content.

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?

With 8 parameters, 88% schema coverage, and no output schema, the description compensates well by explaining the return value (possible_conflicts with judgment material) and the caller-decision workflow. It also covers idempotency and the no-overwrite guarantee, leaving an agent fully equipped to call it correctly.

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 88%, so parameters like type, trust, source, and supersedes are already well-documented in the schema. The description adds the 'first heading becomes the title' nuance for content and implies the conflict semantics for supersedes/superseded_by, but doesn't systematically enrich each parameter. Baseline 3 is appropriate given the high schema coverage.

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 a specific verb (create), resource (memory as markdown original + derived index), and the distinctive mechanism (returns possible_conflicts for judgment). Among siblings like memory_read, memory_update, and memory_forget, the creation purpose is unmistakable without opening the schema.

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 clarifies that nothing is overwritten automatically and that the caller must judge conflicts (supersede, keep both, or correct). Idempotency for identical content is also stated. It doesn't explicitly say when not to use it vs siblings, but the creation role plus the judgment-caller contract provides clear context.

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