replication_spec

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

With no annotations, the description carries the full burden and does substantial work: it declares the read-only nature ('builds nothing, changes nothing'), enumerates what triggers each flag, and explains that multiple readings in a Value cell are averaged. It does not disclose error behavior when MEASURE.md is absent or unparseable, which is the main remaining gap.

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?

Nearly all content is load-bearing (flags, averaging, read-only scope, variant default, export alternative), but it is delivered as one long run-on sentence dense with parentheticals, so nothing is front-loaded and the agent must parse to the end to learn the tool is read-only.

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?

An output schema exists, so return values need no explanation, and the description covers the transformation, the flag semantics, and the read-only scope for a genuinely complex domain operation. The `as_json` parameter and the failure modes are the only substantive omissions.

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 0% across three parameters, so the description must compensate. It does document `variant` precisely ('whose Dims, default: the standard one') and implies `name` as the part being specced, but `as_json` is never mentioned even though the description talks about the Markdown table form — leaving the JSON toggle undocumented in both places.

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?

States a specific verb and resource: it produces a replication spec table by joining MEASURE.md with the script's Dims values, and names the output columns and flags. The domain jargon (Dims, Field, Class, Source) makes the first read opaque, and it never explicitly contrasts itself with siblings like `measure`, `compare`, or `describe_model`, but the operation itself is identifiable.

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?

Usage is implied rather than stated: 'Reads MEASURE.md and the Dims only: builds nothing, changes nothing' tells the agent this is a safe inspection step. The one routing hint is the closing note that the `spec` export format writes the same table to out/docs, which implicitly points at an alternative for persistence, but there is no explicit when-to-use/when-not guidance.

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