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

Annotations already cover the safety profile (readOnly, non-destructive), so the description's added value is elsewhere: it discloses that cards are validated exactly as on commit, and enumerates the completeness rules and the allowIncompleteCards escape hatch. It does not say whether the preview returns per-card error lists (though an output schema exists), so it stops short of full 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?

Five sentences, front-loaded with the no-write guarantee, then the validation contract. Dense but each sentence carries distinct information; the final 'form is not part of speech' sentence is the weakest because it largely restates the schema.

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 preview with an output schema, the description covers the essentials: it validates like a commit, lists completeness criteria, and documents the key language conventions. Remaining gaps are the merge/create flags and the explicit commit-tool relationship, which are secondary for a preview call.

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?

The top-level parameters (targetLang, change) carry no schema descriptions, and the description never explains change's structure, mergeMode, createIfMissing, or collectionUuid. It does compensate somewhat for the nested card rules (required fields, {} markers, article convention, form vs pos), but much of that repeats the already-rich nested card schema rather than adding new meaning.

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 ('Previews a Lingard vocabulary collection/card change') and adds the crucial scope qualifier 'without writing to Firestore', which cleanly separates it from lingard_commit_vocab_changes. An agent can select it without opening the schema.

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 'without writing to Firestore' phrasing implies this is the dry-run step before a commit, but the sibling lingard_commit_vocab_changes is never named and no explicit 'use this before X' instruction is given. Usage is inferable rather than stated.

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