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

With no annotations, the description carries the load and does well: it discloses that dry_run defaults to true and writes nothing, that a real run preserves all earlier prices and only sets price for dates today or earlier, and that create_missing only applies to named rows and never for supplier lists. It stops short of error/partial-failure behavior or duplicate-row handling, which matters for a bulk mutation.

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 action and permissions, then proceeds through columns, matching, create_missing, and dry_run in a logical order. It is dense and runs long as continuous prose, but nearly every clause carries actionable information.

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 six-parameter bulk mutation with an output schema present (so return values need not be described), the definition covers permissions, CSV column contract, matching precedence, missing-item behavior, dry-run default, and date-effect rules. The main gap is bulk-scale behavior: the 2MB csv limit and what happens on malformed or partially invalid rows are unaddressed.

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 83%, so the baseline is 3; the description adds real semantics on top — markup_percent's formula role in converting unit cost to price, effective_date defaulting to the shop's today, and create_missing's narrow scope. That is genuine added meaning rather than restatement.

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 dated prices into the price book from CSV text') plus the source format, which readily separates it from siblings like pricebook_saveItem (single item) and pricebook_list. An agent can identify it without opening 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?

Gives the preconditions (owner or office, needs see_prices and see_costs when cost is present) and the shape of input accepted (standard list vs supplier list needing markup_percent). It never names an alternative sibling such as pricebook_saveItem or imports_run for the one-item case, so the routing guidance is contextual rather than explicit.

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