infer_csv_mapping

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

With no annotations, the description carries the behavioral burden and does it well: it commits to deterministic execution, local-only operation, and no network or staging. It also lists the full return shape and notes that ambiguous signals get explanatory notes, which is richer than a generic 'infers mapping' statement. It does not explicitly state that no side effects occur, but the deterministic/local/no-staging language strongly implies a pure inference operation.

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 compact sentences front-load the most decision-relevant facts: deterministic, local, no network, no staging. The second sentence itemizes the output fields without repeating the schema, and there is no filler or boilerplate.

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 tool has no annotations and no parameter documentation, so the description must compensate; while it discloses behavior and output fields, it omits input semantics and when-to-use guidance. The presence of an output schema reduces the need to explain returns, but the missing parameter context leaves an agent uncertain about how to populate the optional arguments.

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?

The schema provides no descriptions (0% coverage), yet the description does not explain headers, sample_rows, or desired_properties. The phrase 'CSV mapping inference' and the mention of external_id/property mappings indirectly hint at what headers and desired_properties are for, but the optional sample_rows and the relationship between inputs and outputs are left to inference.

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 identifies the function as CSV mapping inference, and the return list (coordinates, external_id guess, typed property mappings, confidence map, notes) makes the output contract concrete. It does not use a direct verb or name a sibling alternative, so it misses the top tier. The deterministic/local framing also separates it from any remote mapping operation, but not from a specific sibling tool.

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 says 'No network, no staging,' which hints at when the tool is appropriate (local deterministic work), but it never states when to choose this tool over alternatives. No sibling is named and no exclusion or prerequisite is given, leaving the agent to infer use cases from the tool name alone.

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