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

Annotations already declare non-read-only, non-idempotent, non-destructive, closed-world. The description adds genuinely new context: the object is created as a *draft* (not sent), lanes are benchmarked against market data on creation, output includes an RFP id and a Builder link, and free accounts are capped at one RFP. That account-limit and draft-vs-sent distinction is not derivable from annotations.

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?

One compact sentence pairing the action, cap, and side effect, followed by one sentence on return value and one on the account limit. Front-loaded with the verb and no filler.

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?

No output schema exists, and the description compensates by naming the return payload (RFP id, Builder link, per-lane benchmarks). The annotations carry the safety profile and the schema carries the parameters. A small gap remains around error handling at the free-tier limit, but the definition is otherwise self-sufficient.

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%, so the schema fully documents title and lane fields, so a 3 baseline applies. The description reinforces the lane cap ('up to 50 lanes') but adds no field-level meaning beyond what the schema provides.

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 ('Create a draft freight RFP'), names the system (FreightFA), and scopes the artifact (up to 50 lanes, per-lane benchmarking). This clearly separates it from sibling read tools like get_rfp and list_rfps.

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?

The description implies the workflow (create a draft, then finish/send it in the RFP Builder via the returned link) and states a hard constraint ('Free accounts can have one RFP'). However, it never explicitly says when to reach for this versus get_rfp/list_rfps or what to do if the account limit is already reached.

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