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

Annotations declare openWorldHint=true, readOnlyHint=false and idempotentHint=false, and the description meaningfully explains the non-idempotent/consumption behavior: "Each question counts toward the account's monthly FreightFA allowance." It also discloses output traits — answers cite sources and may include a priced rate card — which the annotations alone would not convey. Missing only latency/response-time expectations, which keeps it off a 5.

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 sentences, zero waste, and front-loaded with the capability statement before the output, session, and cost details. Each sentence carries distinct information: scope, output format, continuation semantics, and billing impact.

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?

With no output schema, the description carries the return-value burden and does so — answers are source-cited and may include a priced rate card. Combined with the allowance-cost disclosure and session continuation mechanics, nothing an agent needs to invoke this correctly is missing.

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 description coverage is 100% and both parameters (question's 2,000-character limit, session_id's continue-vs-start-new semantics) are already fully documented in the schema. The description restates the session_id continuation behavior without adding format or syntax detail beyond the schema's UUID pattern and null option. Baseline 3 applies.

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 names a specific verb+resource ("Ask FreightFA's AI freight analyst a question") and then enumerates the domains it covers: lane rates, mode choice, capacity, fuel, carrier vetting, market news, RFP drafting. This is clearly separable from the narrow siblings such as estimate_truckload_rate, get_freight_news, or create_rfp — an agent can tell this is the open-ended catch-all analyst rather than a single-purpose calculator.

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 clear context on when to reach for it (broad, plain-language questions spanning many freight topics) and explains the session_id continuation path for follow-ups. It stops short of explicitly naming alternatives or stating exclusions — e.g. that a precise single-mode rate lookup should go to estimate_rail_rate instead — so routing must be inferred from the topic list.

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