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

Beyond the annotations (destructiveHint=true, readOnlyHint=false), the description clarifies the permanence: "cannot be recovered" and "The row is removed from storage, not moved to another tier." It also discloses permission requirements and the distinction from archival, adding meaningful context not present in annotations.

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?

The description is front-loaded with the core purpose and follows with permission, alternatives, an exclusion guardrail, and a parameter clarification. Every sentence adds distinct value with no filler or tautology, making it efficient for its length.

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 provides all necessary context: irreversibility, permission, scoping via playbook_id and key, and clear alternatives when deletion is not the desired action. An agent can safely and correctly decide to invoke this tool.

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?

The input schema already covers both parameters with descriptions (Memory key to delete, UUID or GUID of the target playbook), and schema coverage is 100%. The description's mention of passing playbook_id as UUID/GUID is redundant with the schema, and the key is only described as "by key," matching the schema without adding new semantics.

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 opens with a specific verb and resource: "Permanently delete one memory entry by key from this playbook." It clearly defines scope (one entry, by key, in this playbook) and highlights irreversibility, distinguishing it from archive_memories and consolidate_memories in the sibling list.

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 guidance is provided: "Use archive_memories to keep the entry in the longterm tier, or consolidate_memories to retain child detail under a parent summary." It also states "Do not call this when you only want to hide completed work," and specifies the credential requirement (memory:write or full permission).

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