dedup_scan

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

With no annotations, the description carries full burden. It discloses method (semantic/lexical), exclusion of checkpoint pairs, and non-automatic nature. However, it does not explicitly state whether the tool is read-only or if it has side effects, leaving some ambiguity.

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 concise with a clear opening sentence and uses dash-separated points for additional details. It is front-loaded and avoids verbose repetition, though could be slightly more 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?

The description covers core purpose, method, and exclusions, but lacks parameter explanations. Given 0% schema coverage and 4 parameters, the description is incomplete. However, it does mention output includes method and score, which is useful.

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 0%, and the description does not explicitly explain any of the four parameters (type, limit, domain, threshold). It only implies threshold via similarity score mention. This is insufficient for an agent to know how to set these 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 tool surfaces likely-duplicate/contradictory memory pairs, explains the method (semantic vs lexical), and notes exclusions. It distinguishes itself from sibling tools like link_memories, edit_memory, and forget by clarifying it is not an automatic merge.

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 explicitly says the tool returns candidate pairs for review, not an automatic merge, and mentions subsequent tools (link_memories, edit_memory, forget). It provides context on when checkpoint pairs are excluded and method selection, but does not explicitly state when not to use the tool.

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