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

With no annotations, the description carries the behavioral burden well: it discloses owner-only authorization, all_or_nothing versus per_row write behavior, and dry_run semantics. It does not cover idempotency, preview_hash enforcement, or on_match behavior, but the core write semantics are clear.

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 compact sentences, front-loaded with the owner-only constraint and core action, then mode and dry_run behavior. Every sentence adds useful information without repetition.

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 complex import tool with no annotations and no output schema, the description covers the main write modes and dry_run but omits return/report details and several parameter behaviors. It is adequate but not fully complete for safe 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?

The description adds meaning for mode and dry_run, which the schema does not describe, and clarifies CSV/mapping usage. However, schema description coverage is only 38%, and the description does not explain source, on_match, or preview_hash, leaving several parameters to the schema alone.

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: import customers from a CSV, including one service address each, and notes owner-only access. It is clear, but it does not explicitly distinguish this run tool from the sibling imports_preview tool.

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 useful context such as owner-only use, confirmed mapping, and dry_run, but does not explicitly say when to use this instead of imports_preview or how to obtain the mapping. Usage is implied rather than fully guided.

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