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

Annotations cover read-only, open-world, non-destructive behavior, and the description adds substantial context beyond them: the requested cut must be in the deck, cannot be the commander or protected, safeguards (budget, owned, locked, excluded, color identity, legality, theme, bracket) are preserved, heuristics are not functional equivalence, and tradeoffs/warnings/affiliate summary are surfaced. This is rich behavioral disclosure.

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 dense and front-loaded, with the core action and constraints stated first, then behaviors. It is appropriately sized for a 10-parameter tool, though the sentence listing safeguards is a compressed enumeration that takes some parsing.

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 read-only, open-world tool with no output schema and only 30% schema coverage, the description gives enough to call it correctly and understand safeguards and possible no-op outcomes. It could be more explicit about return shape or how tradeoffs are structured, but the core requirements are covered.

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 30%, so the description must compensate, and it does by naming replaceCard, commander, budget, owned, locked, excluded, color identity, legality, theme, and bracket constraints. It adds meaning beyond the schema for most parameters, though it doesn't clarify maxChanges, qaTest, or deck format nuances already in the schema.

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 states a specific verb (propose one replacement), the inputs (decklist/URL, commander, replaceCard), and the output cap (at most one). It is clearly distinguishable from siblings like upgrade_precon or repair_deck, which address different goals.

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 establishes context (a complete decklist or public URL plus a named cut) and notes it can return no safe swap, which sets expectations about failure. It doesn't name a specific alternative tool or explicitly exclude cases, so it stops 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.