Entity matching

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

Annotations include readOnlyHint=false, openWorldHint=true, and destructiveHint=false, but the description adds a critical behavioral fact: 'Costs credits from the account wallet.' It also discloses output elements 'confidence and reasoning' not present in annotations. No contradiction exists; the description supplements the annotation information.

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 two sentences, with the core purpose front-loaded in an arrow notation ('Two record sets → which rows are the same real-world thing'). Every sentence contributes: purpose, fuzzy-handling capability, and cost. No filler 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?

For a tool with no output schema, the description covers purpose, fuzzy matching behavior, cost, and mentions output components (confidence, reasoning). It does not specify the exact return shape, but the agent has enough to invoke and interpret the result. Given the moderate complexity, this is nearly complete.

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 100%: parameters a, b, and keys each have descriptions ('First record set', 'Second record set', 'Fields that most identify an entity'). The description's 'Fuzzy names, typos, aliases handled' adds marginal context about how keys should be chosen, but does not significantly deepen parameter meaning beyond the 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 states a specific verb and resource: 'Two record sets → which rows are the same real-world thing'. This clearly identifies an entity-resolution action and distinguishes it from generic operations like parserail_compare or parserail_classify. The mention of 'confidence and reasoning' further clarifies the output nature.

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 provides context by noting 'Fuzzy names, typos, aliases handled', which implies when to use the tool (for messy, approximate matching). It does not explicitly name alternatives or when-not conditions, but the context is clear enough for an agent to select it over exact-match or comparison tools.

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