Memory forget

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the destructive nature is covered. The description adds scope ('observation or whole entity') and mentions prompting, though 'Prompts.' is ambiguous and does not describe what happens during the deletion or whether it is reversible. No contradiction with annotations exists.

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 very short and leads with the action, which is good. The fragment 'Prompts.' is not a complete sentence and its meaning is unclear. The description is concise but under-specified rather than tightly informative.

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 is relatively simple, has destruptive annotations, and has an output schema, the description is mostly adequate for basic invocations. Still, it misses important behavioral details such as whether a confirmation prompt appears, whether deleting an entity also removes all its observations, and what happens with an empty 'observation'. These gaps matter for correct use.

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 coverate is 0%, but the description does add meaning by indicating that either an observation or the whole entity can be deleted, which maps to the optional 'observation' and required 'entity' parameters. However, it does not explain how the two parameters interact, such as what happens when 'observation' is omitted or what format these values should take.

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 states a specific verb ('Delete') and resource ('observation or whole entity'), making the destructive purpose clear. It differentiates itself from sibling memory tools (memory_store, memory_link, memory_recall) by describing deletion rather than storage or recall. However, it does not explicitly name related alternatives or fully define what 'entity' means in context.

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?

No guidance is given about when to use this tool versus alternatives. The verb 'Delete' implies this is for removing memories, but there is no explicit context, prerequisites, or distinction from memory_link or memory_recall. The second sentence 'Prompts.' is too vague to serve as operational guidance.

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