memory_contradict

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

Annotations already indicate non-readonly and non-destructive. The description adds valuable context: 'old NEVER deleted', 'stored as a NEW record', and 'linked via a contradicts edge', which goes beyond basic annotation information.

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 extremely concise with two sentences, directly front-loaded with the action and resource, and includes essential behavioral traits without any superfluous information.

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 (3 parameters, no nested objects, output schema exists), the description covers the core behavior, parameter implications, and data integrity rules. It is complete enough for an AI agent to understand usage, though it could optionally mention the output schema.

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 parameters are well-documented in the schema. The description adds moderate value by explaining the overall semantic effect (new record, old preserved, linking edge) but does not add significant details beyond the schema for individual parameters.

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 verb 'Mark a record contradicted' and the resource 'record', and distinguishes from sibling tools like memory_capture and memory_recall by explicitly noting that old records are never deleted and new records are created.

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 (e.g., when correcting or updating a fact while preserving history) but does not explicitly state when not to use or list alternatives. It provides sufficient context for typical use.

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