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

Annotations already declare readOnlyHint, destructiveHint false, and openWorldHint false, so the safety profile is covered. The description adds genuinely non-obvious behavior beyond that: the score is penalized when it rests on inference rather than explicit answers, which changes how an agent should interpret and relay the number. The trailing 'Read-only' merely repeats the annotation and earns nothing.

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?

Two compact sentences that front-load the returned artifacts before the interpretive advice. Almost every clause carries information, with the only clear waste being the closing 'Read-only' that duplicates the annotation. Structure is logical: what it returns, then how to use it.

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 does the necessary work of listing the four return components, which is the main completeness risk for a getter and it is handled. With no annotations gap and a trivial input, what is missing is modest: failure behavior for an unknown material and how the score relates to the check/answer flow in sibling tools.

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?

There is a single required parameter, material_id, with zero schema description coverage, so the description carries the full burden. It only implies the parameter identifies 'a material' — it never says where a valid id comes from (presumably language_list_materials), what happens on an invalid or unknown id, or that the value is an integer id. A one-parameter getter should not leave that unspecified.

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 names the resource (readiness for a material) and enumerates exactly what comes back: a 0-100 score, a status, core-vocabulary coverage, and a one-sentence reason. An agent can tell this is a readiness lookup rather than a vocabulary or transcript fetch. It falls short of a 5 because the action is expressed as a noun phrase ('How ready the caller is') rather than an explicit verb, and no sibling is named to sharpen the boundary.

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?

'Quote the reason rather than the bare number' is real guidance, but it governs how to present the result, not when to call this versus language_start_check or language_get_vocabulary. The reader must infer the trigger (e.g. before deciding whether to quiz on a material). No when-not conditions or alternatives are stated.

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