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

Annotations only say destructive/not-read-only; the description adds real behavioral context beyond that: a two-tier permission model (author vs memory:moderate) and a version-based rejection rule that implies optimistic concurrency control. These are the exact traits an agent needs to call a destructive tool safely.

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?

A single dense sentence with the action front-loaded and no filler. The compressed phrasing ('authors their own, moderators ... any but user-level ones') is efficient but requires a second read, which costs it the top mark.

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 two-parameter, fully documented, destructive operation with no output schema, the description covers authorization and the failure mode well. It stops short of stating whether deletion is permanent/recoverable and what the response returns, which would matter for an irreversible action.

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 coverage is 100%, so the baseline is 3, but the description gives the version parameter a functional role beyond the schema's 'Record version the change is based on' — it is a concurrency token whose mismatch causes rejection. That meaningfully upgrades what the agent knows about the parameter.

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 verb (Deletes) and resource (agent memory record) and scopes it to a user-initiated action, which cleanly separates it from memory_update, memory_read, and memory_create. An agent knows exactly what this tool does without opening the schema.

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?

Provides the governing authorization context: authors may delete their own records, moderators with memory:moderate may delete any but user-level ones, and the call is rejected under optimistic-concurrency conflict. It does not explicitly route between memory_delete and memory_update (e.g. prefer update over delete-and-recreate), so it falls short of full when/when-not guidance.

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