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

With annotations declaring a non-read-only, non-destructive, non-idempotent mutation, the description adds real substance: proposals must be accepted, source rows are never overwritten, reads default to the source, overlay reads mark original value and provenance, and AUTARIO_API_KEY is required. It even states the return value ('returns the proposal ids'), which no output schema provides.

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?

Purpose and payload shape are front-loaded in the first sentence, and the overlay/auth notes come after. There is mild redundancy: 'the source value stays as the original' in sentence two is restated by the 'Overlay rule' sentence that begins 'the vendor's source rows are never overwritten'.

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 4-parameter mutation tool with no output schema, the description covers scope, mutation semantics, acceptance lifecycle, read-path effects, return value, supported table types, and authentication. Nothing an agent needs in order to call it correctly is missing.

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%, including the dataset-level `reason` fallback for entries without their own reason, so the schema already carries the semantics. The description adds only the notion of 'one column' scope and mirrors the source->canonical example, which is a baseline-3 contribution rather than new meaning.

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 ('propose that several source values of one column mean the same thing') plus the exact payload shape (source value -> canonical value with reason) and three concrete examples (campaign spellings, SKUs, 'FB'/'facebook'). This clearly separates it from value-level siblings like propose_corrections, propose_flags, and propose_column.

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?

Gives the triggering conditions well: per dataset and column, for values that are variants of the same entity, and over connector tables or uploads. It also names the follow-on path (accept, then read via query_dataset overlay="with_overlay"). It stops short of explicitly naming when NOT to use it versus propose_corrections or reject_proposals, so it's clear context rather than full alternatives guidance.

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