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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the closing 'Read-only.' is consistent (though redundant) with them. Beyond that, the description adds genuine behavioral context: results are ranked per-material and every row carries the caller's own state (status, confidence, answered-for vs merely inferred), which is information an agent could not get from the annotations.

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 definition is dense and front-loads the most important idea (ranked vocabulary for this material) before the row-level state and the filter guidance. The opening sentence is long and clause-heavy, and 'Read-only.' duplicates the readOnlyHint annotation, but no sentence is filler overall.

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 must explain return values, and it does describe rows (status, confidence, inferred flag) and ranking. It still leaves gaps that matter for correct invocation: the meaning and default of `need`, and what `limit` caps (number of units? ranking cutoff?), which an agent would have to guess.

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, and it only partially does: it explains two of the three `need` enum values but not 'all', and it says nothing about `limit` (1-100) or how it interacts with the ranking. `material_id` is self-explanatory from its name, but the limit and default-mode gaps leave real ambiguity.

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 clearly conveys the resource ('what a material teaches') and the ordering logic ('ranked by how much understanding each unit buys for THIS material'), so an agent knows it returns ranked vocabulary units for one material. The verb is implicit rather than stated as 'get/list', and it does not explicitly distinguish itself from the sibling language_get_words, which weakens sibling differentiation.

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?

It gives concrete guidance for the `need` values ('core' for load-bearing units, 'to_learn' for the short list worth studying before watching), which tells an agent how to select a filter mode. However, it never says when to call this tool rather than language_get_material, language_get_transcript, or language_get_words, and it omits what the default ('all') means.

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