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

With annotations covering only readOnlyHint=false and destructiveHint=false, the description carries the real behavioral load: partial-update semantics, level changes relocating the record, permission tiers (author vs memory:moderate), the side effect that content edits reset the record to personal and unverified, the human-moderator gate on verified/shared, and optimistic-concurrency rejection on stale version. This is materially more than the annotations convey.

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?

It is a single dense semicolon-chained block, but the purpose is front-loaded and nearly every clause carries distinct information (semantics, permissions, side effects, concurrency). It could be broken into shorter sentences for scanability, but there is little filler to cut.

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 an 11-parameter mutation tool with no output schema, it covers permissions, side effects, partial-update semantics, and concurrency adequately. The main omission is what the call returns (e.g., the new version for subsequent updates), which matters for a version-guarded write.

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 the schema already documents every field, setting the baseline at 3. The description still adds cross-parameter meaning the schema does not: that passed fields are replaced (partial update), that level/projectID/repositoryID jointly move the record, and that shared/verified require moderator rights.

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 states a specific verb and resource ('Updates an agent memory record') and immediately scopes the semantics ('passed fields are replaced, and a new level, projectID or repositoryID moves it'). It is unambiguous against memory_read/list/delete/create by name and content, though it never explicitly names a sibling to distinguish itself.

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 gives clear operating context: the update is performed 'at the user's request', authors may edit their own records, moderators (memory:moderate) may edit any but user-level ones, and the call is rejected on version conflict. It stops short of explicitly naming alternatives (e.g., memory_create for new records), so it is clear context without full when/when-not routing.

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