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

Annotations already declare destructiveHint=true and idempotentHint=false; the description adds value beyond that by spelling out exactly what replace destroys (existing rows), the ~8MB size cap, and that the tool is plan-gated. It omits behavior on partial/malformed rows, but the addition over the annotations is substantial.

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 paragraph that front-loads the core operation and then dispatches the mode semantics, size cap, and gating in short clauses. No sentence is wasted.

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 and 50% param coverage, the description covers the critical call decisions: merge mode, row-destruction semantics, size limit, and access gating. It does not describe failure handling for malformed rows, a minor gap given the remaining uncertainty about slug/site_id.

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 only 50%, so the description must compensate. It usefully explains the csv parameter (header row matches field keys, unmatched ignored) and the mode enum semantics including the upsert key requirement, going well beyond the schema's terse 'Merge mode. Default append.' slug and site_id remain unexplained in both places, keeping this from a 5.

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 (collection CSV) and immediately clarifies the header-to-field-key mapping behavior, which distinguishes it from sibling row tools like create_collection_rows or update_collection_row. An agent can identify the operation without reading the schema.

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?

Provides clear context for choosing a merge mode (append default, replace deletes existing rows first, upsert keyed on externalId/id), which is the main decision an agent must make. It does not, however, route the agent away from sibling bulk tools or state when this tool is preferable to create_collection_rows.

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