Find clusters of similar experiences

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

Adds 'deterministic', 'Read-only; nothing is changed', and tells the agent to emit one rule record per cluster, which is useful context on top of the readOnlyHint and idempotentHint annotations. The word 'write' is slightly ambiguous (could be read as mutation), though the following 'Read-only' mitigates it; no direct contradiction with 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?

Three short sentences with no filler and purpose front-loaded. The only minor flaw is the ambiguous 'write' phrasing, which costs a point.

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?

For a simple optional-parameter tool with no output schema, the description gives enough to understand what the call returns conceptually (a rule record per cluster) and its read-only safety. It could be clearer about the exact return payload or cluster format, but it's largely sufficient.

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?

The input schema fully describes both parameters, including defaults, ranges, and meaning; the description contributes nothing about min_size or threshold, so baseline 3 applies.

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?

States a specific action ('deterministic clustering of episodes') and a concrete output ('ONE record with kind='rule'') that generalises them. This clearly separates it from sibling memory tools like recall or transfer.

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?

Implies usage when multiple episodes represent the same underlying lesson and need generalisation into a rule, but it never explicitly states when to prefer consolidate over siblings or when not to use it. There are no exclusion conditions or alternative tool names.

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