memory_forget

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

With no annotations, the description fully discloses destructive behavior: 'Hard-delete', 'no audit trail', and 'ANY match deletes' for OR-combined filters. It explains edge cases like omitting attribute to purge the whole entity, and reports error behavior. This exceeds typical transparency for a destructive tool.

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 well-structured with a short intro, explicit alternatives, and a scoped bullet list. Every sentence adds necessary information for a destructive multi-scope tool; there is no filler or repetition.

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 complexity (8 parameters, 4 scopes, destructive operation, no annotations), the description covers all key aspects: scope-specific filters, required parameters, alternative tools, return shape, and error behavior. The output schema exists, so return details are further supported, but the description already provides ample context.

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 coverage is 0%, so the description compensates thoroughly. It explains every parameter's role within each scope: text/substring/source/episode/tag for memory, entity/attribute for fact/world/lesson, and the lesson mapping ('pass the task as entity'). This adds meaning far beyond the bare 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 opens with a specific verb+resource: 'Hard-delete from one memory store.' It clearly differentiates from sibling tools by explicitly naming memory_fact_set and memory_supersede as alternatives for non-destructive updates. The scopes section further clarifies what the tool does for each store type.

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?

Provides explicit when-to-use guidance: 'Cleanup for junk/test data — no audit trail.' It then states when NOT to use it and points to alternatives: 'For "now wrong, keep history" use memory_fact_set (facts) or memory_supersede (memories) instead.' Scope-specific instructions also clarify parameter requirements per use case.

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