memory_write

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It reveals the key non-obvious trait that this is an indirect append (not a direct .md modification), describes the log as audited, and discloses the special auto-apply behavior for network_fetch entries on flush. It does not cover permissions, failure modes, or reversibility, but the most important side-effect behavior is stated.

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 compact and front-loaded: the core behavior (append to write_log, no direct .md modification) appears immediately. The bilingual translation adds redundant length but not enough to be wasteful. Every fact present is useful, and there is minimal filler.

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 8 parameters, no annotations, and no output schema, the description covers the central mechanism (append to a log, flush-time behavior) but leaves important gaps. It never explicitly instructs the agent to call memory_flush to apply entries, and 'distributed per config' is vague about what happens to each kind after flush. The agent can likely use the tool, but not with full confidence about downstream effects.

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 only 38%, so the description must compensate, but it provides little parameter-level detail. It adds meaning for kind=network_fetch by explaining the related web/ auto-apply behavior, but it does not explain the roles of agent, domain, task_id, ref_paths, or summary, nor does it clarify how the listed kind values map to different outcomes beyond the raw schema string.

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?

States a specific action: 'Append to the audited write_log' and explicitly contrasts itself with direct modifications: 'does NOT modify .md directly'. This clearly differentiates it from sibling tools like memory_update and memory_delete, and aligns with memory_flush. The verb+resource combination is unambiguous.

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 implies the intended write flow: append to the log, then have entries applied on flush. It also provides context for using network_fetch entries, but it never explicitly names alternatives like memory_update or states when to use memory_write vs. the other write-related siblings. The 'does NOT modify .md directly' warning hints at a boundary but leaves the routing to the agent.

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