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

Annotations only declare readOnlyHint=true, so the description carries the burden of explaining behavior, and it does so richly. It discloses the return format (a single batch-quote card with one row per lane), the output fields (origin → dest, mode, pallets, price, transit), that each row keeps quote_id, and that rows can be individually booked. It also clearly warns against overclaiming comparison coverage, which is exactly the kind of behavioral context an agent needs.

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?

The description is compact for the amount of behavioral nuance it carries, and the most important capability is front-loaded. There is a small redundancy—'NOT all-mode or all-carrier comparison' and 'Never imply this tool compared every carrier' say similar things—but both serve as deliberate guardrails. Overall, every sentence earns its place for a tool with no output 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?

Given that there is no output schema, the description fully compensates by spelling out the return shape, row fields, quote_id retention, and booking follow-up. It also covers limitations and sibling routing, which is more than sufficient for an agent to invoke the tool correctly and interpret its response. The input side is fully handled by the high-coverage schema.

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 the lanes array and nested properties. The description adds value by clarifying the row-to-quote mapping ('each row maps to one quote'), the 50-lane invocation model, and the per-row mode default, which reinforces but does not merely duplicate the schema. It doesn't need to restate each lane field, so this exceeds the baseline.

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?

The description states a specific verb ('Price'), a clear resource ('up to 50 lanes in one call'), and the per-row mode behavior. It differentiates this tool from siblings like compare_modes and ltl_market_options by explicitly stating what it is NOT ('NOT all-mode or all-carrier comparison'). An agent can confidently distinguish this from batch_book, ltl_quote, and compare_modes without opening schemas.

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?

It gives explicit when-to-use guidance ('Price up to 50 lanes in one call') and names alternatives with their trigger conditions: compare_modes for Compare All and ltl_market_options for LTL carrier alternatives. It also states a clear exclusion: 'Never imply this tool compared every carrier.' This leaves no ambiguity about when to select this tool versus a sibling.

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