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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds genuinely new behavioral facts: replace deletes existing rows first, upsert keys off an externalId/id column, unmatched columns are silently ignored, there is an ~8MB cap, and the tool is plan-gated. It does not disclose the response shape or whether the import runs asynchronously.

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?

A single dense sentence pair, front-loaded with the core action and then the mode contract. Nearly every clause carries information, though 'CSV text' and the restated default slightly overlap with the schema.

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 destructive, plan-gated bulk mutation with no output schema, the description covers caps, mode behavior, and column handling well. It omits how failures/partial imports behave and, notably, never mentions async execution or status polling despite a get_import_status sibling existing, leaving a real gap for correct invocation.

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 baseline is 3, but the description meaningfully enriches two parameters the schema describes only tersely: it explains the CSV header/field-key contract for `csv` and gives the actual merge semantics (and upsert key) behind the `mode` enum, which the schema's 'Merge mode. Default append.' does not convey.

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 (import) and resource (CSV rows into a collection, implied by the slug param and title). It distinguishes itself reasonably from create_collection_rows and import_site by naming the CSV format and the header-to-field-key matching rule, though it never explicitly says 'into a collection' in the body.

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?

The mode breakdown gives clear conditions for append vs replace vs upsert, which is real guidance on how to invoke it. However, it offers no when-to-use-this-vs-alternatives routing (e.g. vs create_collection_rows for small batches or import_site for whole sites), and no prerequisites beyond the plan gate.

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