anneal-memory

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

No annotations provided, so description carries full burden. Compensates well by extensively detailing return payload (episode counts, wrap history, continuity file size, wrap status). Implies read-only nature via 'Get,' though could explicitly state 'safe to call' given the mutation siblings context.

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 efficient clauses: purpose statement ('Get memory health metrics'), usage timing ('Call this at session start...'), and return value specification ('Returns episode counts...'). Front-loaded with no wasted words.

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?

Rich description compensates for missing output schema by exhaustively listing return fields. Explains domain-specific concepts (wrap, continuity, episodes) necessary to understand tool utility. Complete for a zero-parameter diagnostic tool.

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?

Zero parameters present. Per calibration rules, 0 params = baseline 4. Description correctly omits parameter discussion since schema requires no input.

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?

Specific verb 'Get' + resource 'memory health metrics' clearly identifies this as a diagnostic read operation. Distinguished from action-oriented siblings (prepare_wrap, record, save_continuity) by its observational purpose.

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 states when to call: 'at session start' and 'when diagnosing issues.' Provides clear temporal context for invocation. Could be strengthened by explicitly contrasting with mutation siblings, but the verb choice establishes clear separation.

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