merge_candidates

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

With no annotations, the description carries full burden. It discloses read-only behavior and the Fellegi-Sunter algorithm for match/possible/non-match, providing key behavioral insight without covering rate limits or auth needs.

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 concise sentences: first states core purpose with algorithm and output, second emphasizes read-only nature. No unnecessary words or 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?

Given no output schema, the description covers the main output (confidence scores, signals) but lacks details on candidate cluster structure. With only 2 simple params and read-only nature, it is mostly complete for agent decision-making.

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%, so baseline 3 applies. The description adds no extra meaning beyond the schema-provided parameter descriptions; it only mentions the output (scores, signals) but not parameter specifics.

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 uses a specific verb 'surface' and resource 'likely duplicate/overlapping memory clusters', mentions confidence scores and Fellegi-Sunter signals, distinguishing it from siblings like 'find_duplicates' which likely lacks this algorithm detail.

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 the tool is read-only and 'nothing is changed', guiding when to use for inspection. However, it does not explicitly list when not to use or name alternative tools for actual merging, leaving some inference to the agent.

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