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

Annotations only indicate the tool is a write operation (readOnlyHint: false, destructiveHint: false). The description adds valuable behavioral context: the call is rejected without `lang`, the user has opted into automatic capture, no confirmation is needed, captures happen silently, and honesty is required if asked. This goes well beyond the annotations and sets clear expectations for agent behavior.

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 long but each sentence adds functional value: purpose, user consent, usage policy, batching, language requirements, and capture heuristics. It is front-loaded with the action and destination, then branches into practical rules. While it could be trimmed slightly (e.g., repeating 'capture diligently'), the density is justified by the tool's central role.

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 write tool with no output schema, the description covers the essential operational context: when to use, what to pass, how to structure multiple captures, and critical failure conditions. It does not describe return values or post-capture behavior, but that is not required for a capture action. The main omission is any note about idempotency or capacity limits, but overall it is sufficiently complete for reliable invocation.

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 100%, but the description enriches it: it flags `lang` as mandatory (schema lacks a required list), explains the legacy `word` vs. batch `words` distinction, clarifies `gloss` and `context` usage, and notes `source_lang` defaults to the deck's language. This adds meaning beyond the raw property descriptions, such as the rejection behavior and batching preference.

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 opens with a specific verb+resource: 'Capture a target-language word or phrase to the user's Minddory vocabulary deck,' and clearly distinguishes its scope as the primary word-capture tool, contrasted with siblings like capture_grammar_mistake. It states the exact action, destination, and context (flashcard vs. context encounter), making the purpose 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?

The description provides explicit usage guidance: use proactively, don't pause for permission, don't announce every capture, batch with `words`, skip stop words/proper nouns/numbers/short words, and always pass `lang`. It does not explicitly compare against alternative capture tools (e.g., capture_grammar_mistake), but the context 'primary tracking signal of Minddory' implies precedence. Overall, strong guidance but no explicit exclusions for alternatives.

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