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

The annotations already declare this is a non-read-only, non-destructive, non-idempotent mutation. The description adds genuinely useful behavior beyond that: submissions land in a PROPOSED state requiring human review rather than taking effect immediately, which materially affects how an agent should reason about the result. It does not mention what is returned (e.g. new memory ids, which matter for later supersedes) or any throughput or volume constraints.

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 sentences, front-loaded with the core action and the review-queue caveat, with the atomic/concise constraints and the supersedes workflow following. No filler or restatement of the title.

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?

For a nested-array mutation with no output schema, the description covers the essential points: what qualifies as a memory, how it should be shaped, and how corrections work. The remaining gap is the return value and post-submission lifecycle (are ids returned? does review rejection happen?), which an agent would benefit from knowing but can partly infer from the 'PROPOSED' wording.

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% and every nested field carries its own description, so the schema already carries the parameter burden. The description reinforces two semantics not fully conveyed there - atomicity/brevity of content and the supersedes linkage to search_memory - but adds no detail on repo format, type keys, or confidence.

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 names a specific verb and resource ('Record durable, reusable knowledge ... as PROPOSED memories') and enumerates the knowledge categories (conventions, architecture, commands, risks, decisions). The 'PROPOSED ... for human review' framing distinguishes it from a direct-write or summary tool, though it never explicitly contrasts itself with siblings like record_session_summary.

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?

It states the condition for use (durable, reusable knowledge) and prescribes the correction workflow: use supersedes with an id obtained from search_memory. It also constrains the shape of what to submit (atomic, 1-3 sentences). What is missing is any when-not guidance, e.g. that transient session state belongs in record_session_summary instead.

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