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

While annotations already include destructiveHint=true and readOnlyHint=false, the description adds critical behavioral details beyond annotations: 'This cannot be undone' (irreversibility), 'Deleting a raw memory does not delete reflections built from it' (side-effect boundary), and requiring user confirmation. These details meaningfully inform the agent about consequences and limitations.

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 sentences front-load the core usage constraint, then state the action and side effects, and end with an alternative. Every sentence carries essential information with zero redundancy or filler.

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?

Given the tool's moderate complexity, presence of an output schema, and robust annotations, the description covers all necessary context: when to use, what it does, side-effect nuance, irreversibility, and a sibling alternative. Nothing critical is missing for an agent to select and invoke this tool correctly.

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?

Input schema covers both parameters with descriptions (100% coverage), so baseline is 3. The description adds context that IDs come 'from search or inspect results', which helps the agent know where to source IDs. However, the description does not elaborate on the confirmation parameter, though the schema already fully explains it. Adds modest value beyond schema.

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 clearly states the tool 'Permanently deletes the identified memories from the connected vault by their ids' and explicitly distinguishes it from forget_all_memories for whole-vault deletion. The verb 'delete' plus resource 'specific memories' and scope makes the purpose unambiguous and distinct from siblings.

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?

Explicitly states 'Use this only when the user explicitly asks to delete specific memories and confirms after seeing what will be deleted' and provides a clear alternative: 'For deleting everything, forget_all_memories is the separate whole-vault tool.' This gives both when-to-use and when-not-to-use guidance.

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