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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial non-obvious behavior: compiling a description invokes a language model and requires an access_key, templates are free, and the result includes an `issues` list flagging problems like a floor below cost. These cost/auth/validation traits go well beyond what the annotations disclose.

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?

Well front-loaded: purpose first, then a clearly labeled when-to-use block, then cost/auth, then returns. It is on the long side and the 'Returns {ok, policy, issues, summary}' section is partly redundant given an output schema exists, but each sentence carries information an agent would otherwise have to guess.

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 a 3-param, zero-required, no-enum tool with a full output schema, the description supplies everything missing: which input mode to pick, the auth requirement, the cost model, and the semantic content of the return fields. Nothing an agent needs to select and invoke this correctly is absent.

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 already 100%, so the schema documents all three parameters, making 3 the baseline. The description adds meaning by enumerating what a good `description` should contain (listed price, floor, tradeables, extras and their cost, off-limits items) and by surfacing the three concrete template values, which goes beyond the raw schema text.

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 opening sentence states a specific verb and resource — turning a plain-language seller offer into negotiation rules — and the framing 'RULES an AI agent cannot break' makes the output artifact concrete. It is clearly distinguishable from siblings like check_offer_policy (validation) and draft_negotiation_reply (which consumes this tool's output).

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?

An explicit 'USE THIS WHEN' block names the scenario (selling something where buyers or their agents haggle), and it routes between the two input modes — a free-form description vs. a named template. It even names the downstream sibling (draft_negotiation_reply), so the agent knows where the result flows.

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