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

Annotations already flag non-read-only, non-destructive, non-idempotent; the description adds real value on top by disclosing the additive-only semantics and the read-only status of curated collections. 'commit=true writes' implies commit=false is a dry run, though it is left implicit and error/permission behavior is 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 tight sentences, front-loaded with the core action and the non-overwrite guarantee; every sentence carries distinct information and none repeats annotations verbatim.

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?

The output schema removes the need to describe returns, and annotations cover safety, but for a 5-parameter mutation tool the description leaves card-matching, collection targeting (uuid vs title), and dry-run behavior undefined. Adequate minimum, with clear gaps an agent must guess at.

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?

Top-level schema description coverage is reported as 0%. The description explains only the commit flag; targetLang, collectionUuid, and collectionTitle are entirely undocumented, and nothing says how provided cards are matched to existing cards (title, alias, uuid).

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 ('Fills empty fields on existing Lingard cards') and adds the defining constraint 'never overwrites or clears a field that already has a value', which cleanly separates it from sibling update tools such as lingard_update_example_translations.

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 clear applicability context: works on the user's own collections and the 'Words not in a collection' bucket, and explicitly excludes curated Lingard collections as read-only. It does not, however, point to alternatives (e.g. preview_vocab_changes or commit_vocab_changes) or explain when to prefer them.

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