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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is largely carried by structured data. "Permanent" adds a little emphasis on irreversibility, but the description says nothing about behavior on nonexistent or duplicate ids, partial-failure semantics, or whether any recovery is possible. The multi-step search-then-delete guidance is useful process context but not additional disclosure of the tool's own effects.

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 short fragments, front-loaded with purpose and permanence before the workflow hint, with no filler. The telegraphic style is slightly clipped but every clause carries information.

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 single-parameter destructive tool whose annotations already declare destructiveness and idempotency and which has no output schema, the description covers purpose, irreversibility, and how to source the ids. Nothing an agent needs in order 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 description coverage is 100% and the single `ids` parameter is fully documented in the schema, including an example array. The description's inline `memory_delete(["id1","id2"])` restates that format rather than adding new meaning such as batch limits or ordering guarantees. 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 and resource ("Delete memories by ID") plus an irreversibility marker ("Permanent"), which separates it from memory_edit and memory_retrieve. It does not explicitly name the read-only siblings it is not, so it stops short of full sibling differentiation.

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?

Gives an explicit prerequisite workflow for the harder case: "Delete by filter: memory_search first, collect ids, then delete." That tells the agent exactly how to obtain the required ids. It does not say when not to use it (e.g., prefer memory_edit to correct rather than remove), so no exclusions are covered.

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