ck_memory_record

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

With no annotations, the description fully bears the transparency burden. It discloses the write operation, persistence, idempotency via source_id, memory format flexibility, record_type meanings, and tags handling. This is comprehensive behavioral 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?

The description is relatively long but efficient, front-loading the primary purpose and idempotency. Each sentence adds value, though some redundancy exists (e.g., 'Write operation — persists to the database' is clear). Slight reduction possible without losing meaning.

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 parameter count of 12, schema coverage at 75%, and no output schema, the description adequately covers idempotency, memory structure, record_type options, tags, and source_id linkage. It does not discuss return values, but idempotency and write nature suffice. The mention of sibling tools adds context.

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 already covers 75% of parameters with descriptions. The description adds meaning beyond the schema by explaining the dual format of 'memory' parameter, each record_type's retrieval purpose, and the purpose of source_id linking. It compensates for the remaining 25% with contextual details.

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 the tool writes a governed memory record for retrieval, with a specific verb (Write) and resource (governed memory record). It distinguishes from siblings by naming ck_memory_search as the retrieval counterpart and explicitly contrasting with ck_finding and ck_goal for different use cases.

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 explicitly states when to use this tool ('persist knowledge that should survive session boundaries') and when not to, with clear alternatives: 'Use ck_finding for policy violations with a ruling decision. Use ck_goal for durable multi-session intent.' This provides direct guidance.

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