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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds real beyond-schema context: the overlay rule that vendor source rows are never overwritten, that reads default to source, and that accepted edits carry original value plus provenance. It also names an auth requirement (AUTARIO_API_KEY). Return shape is described only loosely (before/after, reason, who, when) and pagination/limit behavior is not discussed, so not a 5.

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?

Front-loaded with the core action and contents, then alternatives and the overlay rule. It is slightly repetitive: query_dataset with overlay="with_overlay" is stated twice, which costs tokens without adding information.

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?

No output schema exists, so the description usefully sketches entry content (before/after, value, reason, actor, timestamp) and the default state, plus auth requirements and the non-destructive overlay model. Missing are entry ordering, what limit truncation looks like, and any note on connector/upload scope errors, which keeps it from a 5.

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% and includes defaults and enums for kind, state, and format, so the schema carries the parameter burden. The description adds some semantic framing for state (accepted vs. rejected/superseded/all) and for per-entry fields, but nothing about kind, limit, or format beyond what the schema already says.

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 (list the overlay layer of a dataset) and enumerates the contents (accepted derived columns, flags, corrections, mappings) with per-entry fields. It also names the closest sibling (query_dataset with overlay="with_overlay") and explains the difference, so an agent can distinguish them without opening schemas.

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 routes: use this to inspect the overlay records; use query_dataset with overlay="with_overlay" to read rows with edits merged in. It also states who may request non-default states ("the owner may also ask for rejected, superseded or all"), covering when-not-default cases.

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