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

Annotations already declare destructive/idempotent/not-read-only, and the description adds substantial context beyond them: irreversibility, the exact semantics of deleting an already-absent memory ('reports that it is gone and succeeds'), the interaction with agent deletion, an auth prerequisite, and a prompt-injection caveat about memory content. This is well past the annotation bar.

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?

Multi-sentence and fairly dense, but front-loaded with purpose and identity, and each remaining sentence carries a distinct safety or lifecycle fact (irreversibility, ordering, idempotence, injection warning, auth). Nothing reads as filler, though it could be tightened slightly.

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 destructive tool with no output schema, the description covers what gets destroyed, error semantics for missing targets, ordering relative to agent deletion, auth requirements, and the injection risk of the content being handled. An agent has everything needed to call it safely.

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 key/memory/name/org_name are already documented and the tool has no enum or nested structure. The description restates the exactly-one-of-key-and-memory constraint and the id source, which adds marginal reinforcement rather than new semantics, matching the baseline 3 for schema-covered parameters.

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?

Names a specific verb and resource ('Destroy one of an agent's durable memories') and immediately defines the two addressing modes (key or id as list_memories shows them), pointing at the sibling that supplies ids. An agent can distinguish this from list_memories/set_memory 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?

Gives explicit preconditions ('confirm with the user first, naming the memory') and a selection rule ('pass exactly one of key and memory'), plus lifecycle ordering advice (destroy memories before destroying the agent). It does not name a counter-tool for updating instead of deleting, so the alternative path is implied rather than stated.

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