brain_diff

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

Despite no annotations, the description discloses the tool's behavior: it returns a structured changelog with categories (new, updated, recalled, decayed) and mentions the output format from the format parameter. It does not mention destructive effects, rate limits, or auth, but the read-only nature is implied and the description is sufficiently transparent for a diff 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?

The description is extremely concise: two sentences plus a brief example. Every word adds value, with no redundancy. The front-loaded analogy and immediate explanation of the output make it easy to grasp quickly.

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?

Given the absence of an output schema, the description adequately explains the return structure (categories of changes). It also provides an example output. It lacks details on edge cases or pagination, but for a changelog tool of moderate complexity, it is sufficiently 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%, so baseline is 3. The description adds value by explaining the meaning of the parameters in context (e.g., 'since' as time window, 'instance_id' as cache instance) and providing an example that illustrates their usage. The description also clarifies the output structure beyond the schema.

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 communicates that the tool provides a changelog of AI Brain changes, using the analogy 'git log for your AI Brain.' It explicitly lists the types of changes (new, updated, recalled, decayed), which distinguishes it from sibling tools like brain_search and brain_predict.

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 suggests usage for weekly reviews with the example 'What did my AI learn this week?' and provides a concrete usage example. It does not explicitly state when not to use it or compare to alternatives, but the context is clear enough for an AI agent to determine appropriate use.

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