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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds genuinely non-derivable context: "Needs the seller's sign-in," an auth precondition the agent cannot infer from any structured field, plus a summary of what the payload contains.

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 tight sentences with no filler, and the core purpose plus return contents are front-loaded. The middle clause ("with its type, options, bounds and when it applies") is dense but each item earns its place as a description of the returned spec.

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 burden of describing the return value, and it does so at a reasonable level (fields, types, options, bounds, applicability). No required params, three optional enum filters, and the auth caveat is disclosed — only the meaning of the individual filters is thin.

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 only 33% — only "deal" is documented in the schema. The description gestures at the other two by naming "kinds" and "building types" as the subject matter being filtered, but it never states that kind and building are optional narrowing filters or what distinguishes home/shop or the five building values.

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 makes clear this returns the specification a listing draft requires — the kinds, building types, general fields, and per-fact type/options/bounds/applicability. That is a concrete resource description, though the verb is implicit ("What a listing draft asks") and no sibling is named for contrast.

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?

"Call it before asking the seller" is an explicit sequencing instruction, and "narrow it with kind, building and deal" tells the agent how to scope the call. It lacks an explicit when-not-to-use or a mention of the draft siblings (save_draft, discard_draft), so it falls short of a 5.

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