Landfiller

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

Goes beyond the annotations (readOnly/openWorld/no destruction) by disclosing that shopping imports match by card name, that printing and final prices may differ, and that the agent should surface warnings rather than describe a deficient build as optimal. It does not address the non-idempotent hint — that repeated calls may yield different prices/results.

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: purpose first, then return values, then the safety/preview constraint and the warning-fidelity instruction. Every sentence adds information and the key constraints are front-loaded.

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 enumerates the return payload (quantities, reasoning, prices, coverage, warnings, links) and clarifies side-effect behavior. It is nearly complete for a 6-parameter tool, though the bracket and excludedCards semantics remain unaddressed anywhere.

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 description coverage is 0%, so the description must carry parameter meaning. It covers budget (budgetUsd), acceleration (includeAcceleration), land count range (30–42), and the commander implicitly, but says nothing about bracket or excludedCards, leaving two of six parameters undocumented.

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 (Generate), resource (lands for a Commander mana base), and scope (30–42 lands within a USD budget, optional acceleration). This clearly distinguishes it from the search_commanders sibling, which finds commanders rather than building decks.

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?

Explicitly frames the tool as preview-only with no saved build, email, purchase, or cart modification, which tells the agent its invocation is safe and non-persistent. It does not explicitly compare against search_commanders or state when-not to use it, so it stops short of full routing guidance.

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

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

Annotations already cover the safety profile (readOnly, idempotent, openWorld, non-destructive), and the description adds real operational context on top: autocomplete may surface non-commander cards and only the primary field is validated as a legendary creature. That is the kind of data-quality caveat an agent cannot infer from structured fields; only return format/pagination is left unstated.

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 short sentences, front-loaded with the core action, then the caveat, then the downstream pointer. Every sentence carries information; the middle autocomplete sentence is slightly tangential but relevant to result reliability.

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 single-parameter, read-only search with no output schema, the essentials are present: what it finds, the validation caveat, and where the result feeds next. It does not describe the shape of the returned candidate list, which is a minor gap given no output schema exists.

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 one parameter at 0% schema description coverage, so the description must carry the burden. It implies the query is a commander name ('by name', 'use the exact commander name') but gives no syntax, matching behavior, or partial-match expectations beyond what the schema's minLength/maxLength constraints already convey.

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 concrete verb and resource ('Find Commander candidates by name') and names the downstream sibling build_mana_base, so an agent can tell what it produces. It stops short of an explicit differentiation statement from build_mana_base, but the intent is unambiguous.

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?

'Use the exact commander name for build_mana_base' ties this tool to a concrete downstream condition, effectively telling the agent when to reach for it. No explicit when-not-to-use guidance is given, and the autocomplete caveat is a quality note rather than an alternative-selection rule.

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