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

With no annotations, the description carries the full burden and does substantial work: it discloses the auth tier (Ultimate), the unit convention (USD cents), the exact per-band metrics returned, and the citation obligation tied to the returned `url`. It doesn't cover failure modes or rate limits, which keeps it below 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 tight sentences ordered by importance: what is returned, what is required to call it, and how to cite the result. No filler, no repetition of the title, and the citation rule is actionable rather than decorative.

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 fully compensates by naming every returned metric, its unit, and the included `url` field. It omits edge-case behavior — e.g. items with no listings in a band, or error responses — which is the only meaningful gap for a one-parameter read tool.

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?

There is a single parameter with 100% schema description coverage, including format guidance and a pointer to search_items for loose names, so the schema does the heavy lifting. The description only reinforces the "one item" scope, adding little beyond structured data — baseline 3 is appropriate.

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 — a BUFF price ladder by float range for a single CS2 item — and enumerates what each band contains (lowest ask, average ask, highest bid, listing counts). This is clearly distinguishable from siblings like get_price and price_history, which return single-point or time-series data rather than float-band granularity.

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?

"for one CS2 item" establishes the per-item scope, and the Ultimate-tier key requirement is a concrete precondition an agent must check before calling. It stops short of explicitly naming when to prefer this over get_price or compare_markets, but the float-band focus makes the intended context evident.

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