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

Annotations only declare the generic write profile (readOnly=false, destructive=false, idempotent=false); the description adds non-obvious behavior the annotations can't express: all-or-nothing atomic validation, errors that name the failing rowIndex, a 500-row cap, and a plan-gated prerequisite. This is exactly the context an agent needs before committing a bulk write.

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?

Three telegraphic clauses, front-loaded with the operation and its limits; the sibling pointer is placed last where it belongs. No filler or restatement of the title.

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 mutation tool whose safety profile is covered by annotations, the description supplies atomicity, limits, error shape, plan gating, and an alternative route. The only real omission is any hint of the success response, which is minor given no output schema is required to be explained.

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%, so the schema already documents slug, rows, and id; baseline would be 3. The description goes slightly beyond by clarifying that each row object is a field key → value map and by restating the 500 max on rows, which helps the agent build the payload correctly.

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 (insert rows into a collection) plus scope (up to 500, one call), and implicitly distinguishes itself from the single-row sibling create_collection_row by stating batch capacity. An agent can identify the tool from the first clause alone.

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?

Routes the agent explicitly to import_collection_csv when the payload is a big CSV, and the 500-row ceiling implies the threshold for switching. It does not state a negative condition beyond that (e.g., use create_collection_row for a single row), but the batch-size cue covers the main routing decision.

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