memory_write

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

With no annotations, the description carries full responsibility for disclosing behavioral traits. It adds value by emphasizing falsifiability and the guardrail_level requirement, but it does not describe side effects (e.g., whether it overwrites existing memories, validates evidence, or returns a confirmation). It is a mutation tool, and such omissions are notable.

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 three sentences with no wasted words. It front-loads the primary purpose, then provides the most critical usage constraint (falsifiability), then the conditional guardrail instruction. Every sentence contributes to correct usage.

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 tool has 7 parameters (2 required) and no output schema, the description is reasonably complete for authoring a memory. However, it does not mention what the tool returns or any effects on existing memories (e.g., conflict resolution, deduplication, idempotency). For a write operation, some expectation-setting on return or failure modes would improve completeness.

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 description coverage is 100%, so on its own the schema documents all parameters. The description repeats the falsifiability requirement from the claim schema and the guardrail_level requirement from its schema, adding little new meaning beyond a stylistic emphasis on evidence. It does not explain parameter relationships or edge cases beyond what the schema already states.

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 action ('Persist a new memory') and the resource ('about this codebase'). It goes beyond a tautology by specifying the required format for the claim (falsifiable) and guidance on evidence. It does not explicitly contrast with siblings like memory_propose or memory_search, but the purpose is distinct enough for an agent to recognize it as the write operation.

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 provides clear context on when to use the tool ('Persist a new memory') and offers specific conditional guidance for GUARDRAIL kind. It does not mention when not to use the tool or name alternative tools, but the 'when' is unambiguous. The advice to attach evidence whenever possible gives usage direction.

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