correct

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

With no annotations provided, the description carries the full burden of disclosure. It states the side effect: increments correction count and lowers confidence score, which is a key behavioral trait. However, it doesn't mention reversibility, permissions, or any additional consequences beyond the confidence adjustment.

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, front-loaded with the main purpose, and includes the usage guideline in a compact second sentence. Every word earns its place, with no fluff or redundancy.

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?

The description adequately explains the tool's function and effect, given the simple schema and no output schema. It covers the 'when-to-use' and the impact on future searches. A minor gap is not differentiating when to use correct vs. forget or supersede, but overall it is sufficiently complete for a basic correction tool.

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 both parameters (reason and capture_id) already have descriptions. The tool description adds minimal new meaning, only clarifying that the reason is an explanation of why the memory is wrong, which is largely redundant with the schema. This aligns with the baseline of 3 for high coverage.

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The description clearly states the tool's purpose: 'Mark a memory as inaccurate or outdated.' It also explains the mechanism (increments Bayesian correction count, lowers confidence) which distinguishes it from siblings like forget or supersede. The verb and resource are specific, and the effect on future searches adds unique value.

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 guidance on when to use it: 'Use when a recalled memory was wrong, misleading, or superseded by newer information.' This gives clear context, but it does not mention when NOT to use it or alternatives like forget or supersede, which are present in sibling tools.

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