memory_forget

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

The description discloses a critical behavioral trait: dry-run by default, requiring confirm:true to actually delete. This is valuable safety-relevant context beyond the schema. It also clarifies that query-based removal uses semantic matching. However, it doesn't mention what happens to related data, whether deletion is reversible, or what the dry-run output looks like, but the core safety behavior is well covered.

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?

One sentence, front-loaded with the primary action, and the safety-critical dry-run behavior is included compactly. Every word earns its place; no 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?

For a deletion tool with no annotations and no output schema, the description covers the essential safety behavior (dry-run default, confirm flag) and the two deletion modes. It could be more complete by describing the dry-run output format or clarifying that id and query are mutually exclusive, but the core information an agent needs to avoid accidental deletion is present.

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 coverage is 100%, so the schema already documents all four parameters. The description adds the crucial semantic that confirm gates actual deletion and that query removal is semantic, but it doesn't add detail beyond the schema for min_similarity or id. Baseline 3 is appropriate since the schema carries the parameter documentation burden.

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 ('Remove') and resource ('specific memories'), and distinguishes two modes: by id or by semantic query. It also clearly signals the dry-run default, which differentiates it from sibling tools like memory_clear (which likely removes all memories) and memory_search (which only retrieves).

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 when to use this tool: when you need to delete specific memories by id or by semantic query. It doesn't explicitly name alternatives or exclusions, but the dry-run default and confirm flag provide clear operational guidance. Sibling names like memory_clear and memory_search make the context understandable, though explicit when-not-to-use guidance would be stronger.

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