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

Annotations already declare read-only, idempotent, and non-destructive properties, so the description's burden is lowered. It adds valuable behavioral context by detailing the output components (priced table, market-price estimate, unresolved lines with suggestions, affiliate-wrapped link) and the affiliate aspect. It does not mention edge cases like empty input or rate limits, but given the annotation coverage and the useful output details, this is a solid 4 with no contradictions.

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?

The description is moderately long but packed with essential information: purpose, input format, examples, and output summary. It is well-structured, starting with the core action and then providing format details. While not as terse as a two-sentence definition, it avoids fluff and efficiently conveys all necessary usage cues. The structure effectively guides the agent.

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?

For a tool with two described parameters, the description covers what an agent needs to invoke it correctly: input format, optional parameter, expected output components, and the affiliate link. It doesn't specify error handling or pagination, but these are not critical for basic usage. The description fully prepares the agent to call the tool with confidence, especially given the annotations covering safety.

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 100% (both 'deck' and 'game' have descriptions), and the tool description enriches these with concrete examples ('4x Lightning Bolt', '2 Counterspell (7ED)') and clarifies the expected line format. The optional 'game' hint is explained as a disambiguation aid. This exceeds baseline schema info, making parameter semantics very clear and actionable.

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 clearly states the action (prices a pasted decklist), the resource (decklist from any TCG), and the output (TCGplayer cart link). It provides specific examples of input format and enumerates the returned data, effectively distinguishing it from siblings like price_card, which handles individual cards, and list_printings, which focuses on printings. The purpose is unambiguous and specific.

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 includes explicit instructions on how to format the decklist ('one card per line, quantity + name') and mentions an optional game hint for ambiguous cases. It indicates the tool's broad applicability across many TCGs. However, it does not explicitly state when to prefer this tool over price_card or market_index; the usage context is implied rather than directly contrasted with alternatives. This earns a 4 for clear guidance without explicit exclusions.

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