memory_detect_supersessions

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

The description discloses key behaviors: uses neutral LLM classification, creates edges, supports dry-run, and has a 120s rate limit. It does not mention idempotency, side effects beyond edge creation, or required permissions. Since no annotations are present, the description carries the full burden and does a good job overall.

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 well-structured: a concise purpose statement, functional explanation, bulleted args, return summary, and rate limit note. It is front-loaded with the most critical information and contains no redundant text.

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 covers purpose, mechanism (LLM), parameters, return format, and rate limiting, and differentiates from a sibling. It lacks mentions of prerequisites (e.g., pre-existing embeddings) or performance implications, which would enhance completeness.

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?

With 0% schema coverage, the description compensates by listing all five parameters with clear purposes, defaults, and explanations (e.g., dry_run for preview). This adds significant meaning beyond the raw schema.

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 it detects memories that supersede others, scans for pairs, and creates edges. It distinguishes itself from memory_absorb which catches supersessions at write time.

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 mentions that it complements memory_absorb, implying it is for retroactive detection. However, it does not provide explicit when-not-to-use scenarios or alternative tools under specific conditions.

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