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

While annotations already declare read-only and idempotent, the description adds error-handling behavior: 'never raises a protocol error — it returns an error object.' It also hints at retry safety: 'it is always safe to retry,' which goes beyond the structured annotations.

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 well-structured and front-loaded with a clear purpose statement. It's a bit long but each sentence provides value, such as usage, error semantics, and idempotency. Slightly verbose but justified.

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?

Covers purpose, use cases, non-use cases, error behavior, retry guidance, and includes an output example. With annotations and output schema already present, this description is comprehensive and complete.

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 100% with clear descriptions for 'before' and 'after'. The description adds a concrete JSON example showing expected structure, but this is more illustrative than adding new semantic meaning. Meets the baseline without adding significant parameter-specific insights.

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 'Say exactly what changed between two versions of a memory,' a specific verb+resource that clearly defines the tool's purpose. It differentiates from siblings by stating 'Not for merging the two' and pointing to graph_upsert, making the distinction explicit.

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 explicit use cases: 'Use after an upsert... or between two agents.' It also states what not to use it for and directs to an alternative: 'feed the differences back through graph_upsert for that.'

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