audit_deck

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

With no annotations, the description carries the full behavioral burden and does well: it names an external dependency (Commander Spellbook), discloses the counting methodology, states the return semantics, and explicitly bounds the result as 'what the cards permit' rather than a power verdict. It stops short of noting cost, latency, or failure modes of the external lookup, which is the only remaining gap.

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?

Front-loaded with the action, then methodology, then the caveat — a sensible order with no filler sentences. The closing 'Report it as…' line is arguably guidance for the agent's narration rather than tool behavior, but it earns its place given the misuse risk it prevents.

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?

An output schema exists, so return-value explanation is not owed, and the description compensates well for the absence of annotations by covering inputs counted, external calls, and the interpretive bound. The one substantive hole is the format of the 'deck' argument, which the schema leaves blank and the description never fills.

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 0% — the single required parameter 'deck' is typed only as a bare string with no title or description. The description gestures at the value ('a ManaPool deck', 'the card list') but never resolves whether the agent should pass a deck ID, a URL, or a raw pasted decklist, which is exactly the ambiguity that causes malformed invocation for a lone required field.

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 ('Check a ManaPool deck against the official Commander bracket criteria') and then enumerates exactly what it measures: Game Changers, mass land denial, extra turns, tutors, and Commander Spellbook combos. The output ('lowest bracket the card list mechanically permits') is concrete, and the function is clearly distinct from get_deck, search_decks, and price_deck.

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?

Usage is implied rather than stated: an agent can infer this is the tool for bracket evaluation, but there is no explicit 'use this when…' clause, no mention of how to obtain the deck first (e.g., via get_deck), and no exclusion of alternatives. The second paragraph gives interpretive guidance about how to report results, which is useful but is not when-to-use routing.

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