memory_write

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

No annotations are provided, so the description carries the burden of behavioral disclosure. It clearly indicates this is a write operation ('persist'), but it does not disclose side effects such as immutability, overwrite behavior, permission requirements, or whether the memory is immediately active or goes through a review process. The instruction for guardrail_level hints at enforcement but does not explain what the tool does after writing.

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 long, front-loaded with the core purpose, and each subsequent sentence earns its place by adding parameter behavior guidance. No fluff or repetition.

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, no output schema, and no annotations, the description covers the essential purpose, claim quality, evidence usage, and the guardrail special case. However, it does not explain what the tool returns (e.g., memory ID, success signal) and does not clarify how memory_write differs from sibling memory_propose, which is likely important for an agent deciding between the two.

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 high (86%), so the baseline is 3. The description adds valuable semantics by instructing that claims must be falsifiable, evidence should be attached, and guardrail_level is required specifically for kind=GUARDRAIL. This goes beyond the raw schema by providing conditional logic and qualitative guidance for parameters.

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 opens with 'Persist a new memory about this codebase', which is a specific verb+resource combination. It clearly distinguishes from sibling tools like memory_search and memory_verify by emphasizing 'new' and 'persist'.

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 clearly implies when to use this tool (to store a new memory) and provides substantive guidance on how to craft the claim (falsifiable) and when to attach evidence. However, it does not explicitly mention alternatives or exclusions, such as when to use memory_propose instead of memory_write.

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