memory_refute

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

With no annotations, the description carries the full burden. It discloses a key behavioral consequence: 'Refuted memories are kept as negative knowledge,' indicating a non-destructive action and a persistent outcome. It also mentions the optional superseding connection. It stops short of describing return values or permissions, but the most important behavior is 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?

Three short sentences, with the main verb+resource in the first sentence. Each sentence provides distinct value: the action, the optional parameter, and the behavioral consequence. No redundancy or filler, making it highly efficient 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 tool with only two parameters and no output schema, the description supplies all essential context: what it does, when to use it, the optional input, and the outcome (negative knowledge). It's self-contained and leaves no critical gaps for an agent to invoke it 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?

The schema already describes both parameters with 100% coverage. The description adds context by explaining that the 'superseded_by' parameter is optional and its purpose ('Optionally provide the id of a new memory that supersedes it'), which reinforces the schema. It doesn't introduce new parameter details beyond that, matching the baseline for well-covered schemas.

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: 'Mark a memory as REFUTED' and clarifies the action's trigger. It distinguishes this tool from siblings like memory_verify or memory_write by focusing on the unique refutation action, so there's no ambiguity about its purpose.

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?

It explicitly states when to use the tool: 'when you discover it no longer holds.' It also indicates the optional behavior of providing a superseding memory, which guides usage in that scenario. However, it doesn't name alternative tools or explicitly state when NOT to use it, so it's clear but not exhaustive.

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