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

Annotations already declare readOnly/openWorld/non-idempotent/non-destructive, and the description reinforces rather than contradicts them with 'Nothing is purchased or saved publicly.' It adds behavior the annotations cannot: URL imports drop sideboards and Moxfield companions, provider access can fail, owned is capped at 150 entries/100 copies, and bracket analysis is guidance rather than certification.

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?

Purpose and input contract are front-loaded, and nearly every sentence carries operational content (input formats, caps, return payload, safety). It is dense and reads as a wall of clauses rather than cleanly separated sections, but there is little pure filler to cut.

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 10-parameter, no-output-schema tool, the description explicitly enumerates the return payload (cuts/additions, role counts, warnings, cost, card links, cartUrl), which removes the need for an output schema. The main incompleteness is the unexplained bracket and maxChanges parameters, plus no guidance on what values of bracket mean.

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 30%, so the description must compensate, and it does for the highest-risk fields: budget is USD, owned is a quantity-prefixed list with entry/copy caps, locked and excluded are newline-separated card names (neither has a schema description), and replaceCard restricts review to one non-protected card. It leaves bracket and maxChanges undefined in both schema and description, which is the remaining gap.

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 ('Upgrade a Commander precon using preconworkshop') and immediately defines the accepted inputs. The scope is clearly narrower than siblings like build_mana_base or reduce_deck_cost, but no sibling is named explicitly, so an agent must infer the boundary rather than being routed.

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?

Gives concrete conditions: full quantity-prefixed decklist or public HTTPS Moxfield/Archidekt URL, a fallback when provider access fails ('request a plain-text export'), and an optional narrowing via replaceCard. It also instructs the caller to show warnings and let the player choose swaps. What's missing is explicit when-not guidance relative to repair_deck, reduce_deck_cost, or change_deck_bracket.

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