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

Annotations (`readOnlyHint: true`) already cover read-only safety. The description goes beyond this by explaining the grouped output lists (`not_in_deck`, `known`, `struggling`), the `skipped` array behavior with the `answered_as` field, and the defaulting behavior of `lang`. The only minor gap is not detailing pagination or rate limits, but the provided context is substantial.

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 dense but packed with valuable information, front-loading the main purpose. It covers usage, return structure, edge cases (`skipped`), and defaults. The only slight miss is being somewhat lengthy, but every sentence earns its place, making the informational density high.

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 batch lookup tool with 2 params and no output schema, the description thoroughly explains the return values (mastery levels, `skipped` handling, `lang_defaulted`). It covers the main use case (pre-glossing check) and edge cases (duplicates, unknown languages), making it highly complete.

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 input schema already has 100% coverage with useful descriptions for both `words` and `lang`. The description adds crucial information about the return structure, which the schema lacks. However, the schema already explains the parameters well, so while the description enhances understanding of behavior, it doesn't add significant semantic detail about the parameters themselves beyond what's already in the schema.

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 and resource: 'Batch lookup: for a list of target-language words, tell me which ones are already in the user's Minddory deck and how well they know each.' It clearly explains the batch nature and differentiates itself from siblings like get_card by stating 'Prefer this over calling get_card once per word.'

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?

Provides explicit instructions on when to use it ('Use this BEFORE glossing or capturing vocabulary from a message'), what it answers ('which of these are actually new to this user'), and explicitly names the alternative ('Prefer this over calling get_card once per word'). This meets the criteria for explicit exclusions and alternatives.

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