infer_type

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

No annotations are provided, so the description carries the full disclosure burden. It communicates coordinate semantics (1-based line/column) and that the tool returns type/effect-row information, but it doesn't explicitly say whether the operation is read-only, what it returns in full, or how failures and edge cases are handled.

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?

Single clear sentence, front-loaded with the main action and the key location constraint. There is no filler or repetition.

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 three simple required parameters, the description is minimally adequate, but with no output schema and significant sibling ambiguity, it should say more about expected output or alternatives. It gives useful location details but leaves the agent infer the rest.

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%, and the schema already documents the 1-based and .hird details for all three parameters. The description only groups them as a location, adding no significant meaning beyond the structured 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 uses a specific verb ('infer') on a specific resource (the expression at a source location in a .hird file) and states the output concept (type and effect row). It does not explicitly distinguish itself from sibling tools such as explain_effect_row or lookup_definition, so it misses full differentiation.

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?

It gives no guidance about when to use this tool instead of the available siblings, and no prerequisites or exclusions are mentioned. The only usage context is implied by the mention of a source location.

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