memory_crystalize

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

Describes key behaviors: compresses last 30-50 sessions, crystals persist across cleanup, appears in session_start. However, it does not clarify if original sessions are affected or destroyed.

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 sentences, front-loaded with action, no redundant information. Every sentence adds essential context.

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 what, when, and return value. Lacks prerequisites and error conditions, but sufficient for standard use given no output schema.

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?

Adds value for 'label' by noting auto-generation from date; for 'instance_id' it repeats schema info. Overall improves understanding beyond 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 states it compresses sessions into a Memory Crystal, a structured summary, and distinguishes it from other brain-related tools by specifying its permanent nature and appearance at session start.

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?

Explicitly recommends running monthly or after a big milestone, but does not contrast with similar siblings like memory_consolidate or provide when-not-to-use scenarios.

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