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

Adds substantial context beyond the annotations: the source value is never overwritten, corrections become stale rather than masking a provider revision, proposal ids are returned, and AUTARIO_API_KEY is required. The annotations already declare destructive=false and idempotent=false; the description would ideally warn that repeated calls create separate proposals, which is the one meaningful behavioral 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?

Front-loads the core action and its return, then backs into the overlay/staleness model. The overlay explanation occupies several sentences (stale behavior, overlay rule, query_dataset overlay param) and could be tightened, but each sentence supplies non-obvious semantics rather than filler.

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?

There is no output schema, yet the description states what comes back (proposal ids) and covers lifecycle (stale corrections), data sources, auth, and the read path for seeing merged edits. Remaining gaps are minor, mainly what happens if a proposal is duplicated or how corrections relate to accept_proposals/reject_proposals.

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%, so dataset_id, corrections, row_key, column, value, and both reason levels are already documented in structured form. The description reinforces the one-entry-per-cell and per-entry-reason model but adds no format or constraint detail (e.g. valid column names, row_key sourcing) beyond the schema, so the baseline 3 applies.

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 corrections of single cells of one of your datasets') plus the unit of work (one entry per cell, each with a reason). It scopes which sources apply (connector tables such as Meta Ads, Google Ads, Shopify, plus uploads), which separates it from siblings like write_rows, propose_column, propose_flags, or propose_mappings.

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 a clear usage context: use it for cell-level corrections and read results back with query_dataset overlay="with_overlay". It does not explicitly say when NOT to use it (e.g. use accept_proposals to approve, write_rows to change upload rows directly), so the agent must infer the alternative routing, but the situation is otherwise unambiguous.

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