Забути факт

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

No annotations are provided, so the description must fully disclose behavioral traits. It states that rows containing the text are removed, but does not mention that this is permanent/irreversible, that all matching rows are affected, or any side effects. The philosophical note adds no operational transparency.

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 two sentences, with the operational purpose front-loaded. The second sentence is a philosophical justification that is not needed for function but is short. Overall concise and well-structured.

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 simple one-parameter destructive tool without annotations, the description is adequate but lacks explicit statements about permanence, effect on all matches, or return value. It implies destructiveness but does not state it clearly, which is a gap given the absence of annotations.

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 schema description for 'contains' is minimal ('fragment of row to remove'), but the tool description clarifies that matching is substring-based ('rows that contain the specified text'), which adds semantic meaning beyond the schema. This is useful for the agent.

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 action: 'removes from memory rows that contain the specified text'. The verb and resource are specific, and it is distinct from siblings like memory_add and memory_read. No ambiguity about what the tool does.

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?

The description implies a use case ('a fact that has become false is more harmful than its absence') but does not explicitly state when to use this tool versus alternatives like memory_add or memory_read. There is no mention of conditions where this tool should not be used.

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