dedup_candidates

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

Discloses output (sorted pairs), exclusion of auto-merge pairs, and sorting behavior. Though no annotations, the description adds good behavioral context, but lacks explicit side-effect statements.

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?

Three concise sentences, each adding distinct value: action, purpose, output characteristic. No 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?

No output schema, but description explains output (sorted pairs). References auto-merge threshold concept. Could detail pair structure more, but sufficient.

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 coverage is 100% with descriptions. The description adds value by explaining the threshold parameter's role relative to the auto-merge threshold.

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?

Description clearly states it returns pairs of nodes with embeddings between a threshold and auto-merge threshold, distinguished from sibling tools like canonicalize_node and 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?

Explicitly states intended use for human review before calling canonicalize_node, providing clear when-to-use context and implicit alternative.

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