memory_contradict

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

The description explicitly states 'Mutates store' and 'old NEVER deleted', adding critical non-destructive mutation context beyond the annotations. It also clarifies that the new fact becomes a separate record, which is a key behavioral trait not fully captured by the readOnlyHint/destructiveHint flags.

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?

Two short sentences deliver the essential facts: the action, the storage behavior, non-deletion, and mutation. No filler or redundant repetition of schema content. Well front-loaded and concise.

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 straightforward mutation with a rich schema and output schema present, the description provides sufficient context. The non-destructive nature and new-record behavior are disclosed, which is the core complexity. The output schema handles return-value documentation.

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?

All parameters have detailed descriptions in the schema (100% coverage), so the description adds no additional parameter-level meaning. The schema already covers id and new_fact semantics, including the contradicts edge, making the description unnecessary for parameter understanding.

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' and the resource 'a record', and specifies that a new fact is stored as a NEW record while the old is preserved. This distinguishes it from sibling write tools like memory_capture by focusing on contradiction rather than simple creation.

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 implied usage is that you call this when needing to contradict an existing fact, but no explicit when-to-use vs alternatives is provided. The description does not exclude any cases or name alternatives, leaving usage inference to the name and sibling context.

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