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

No annotations are provided, so the description carries the full burden and does so: it discloses the write is a soft-delete (not a hard purge), the memory:delete permission requirement, the caller-visible failure mode (deleted:false, reason:not_found) including deliberate masking of another member's private memory, and actor-type gating. These are behaviors an agent could not infer from the schema alone.

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?

Core purpose and permission are front-loaded, then parameter provenance, then exclusions and caller-class gating. Every sentence carries a distinct decision-relevant fact; there is no restatement of the tool name or padding.

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?

Output schema exists, so return values needn't be explained, yet the description still discloses the not-found return shape. For a mutation tool with no annotations, permission, caller gating, input provenance, sibling exclusion, and failure semantics are all covered — nothing an agent needs to call it correctly is missing.

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%, and the description largely repeats what the schema already says (memory_id is the memory_items UUID from a previous recall; reason is an audit reason). It adds the useful constraint that only recallable rows are forgettable, but parent_id is given no meaning in the description at all. Baseline 3 is appropriate when the schema does the heavy lifting.

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+resource+scope: soft-delete of a semantic/episodic memory by id, with the required permission. It actively distinguishes itself from siblings by ruling out procedural deletes (memory_forget_procedure) and by refusing agent seats. An agent can place it precisely in the memory_* family without opening any 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?

Explicit when-not conditions (procedural deletes unsupported; agent seats refused) and explicit routing alternatives (request_gated_approval with gate="destructive") for the refused caller class. It also states the acceptable input provenance — only a row you can recall — which is effectively the precondition for use.

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