Get a chapter, topic or item by ID

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, so safety and determinism are covered. The description adds genuinely new behavior: each ID kind returns different structure (sections, subtopics, neighbours), every result carries an official PDF page and a verified flag, and textbook text is explicitly out of scope. It is silent on what happens with an invalid or ambiguous ID, which is the main residual gap.

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 sentences, front-loaded with the returned-resource description and ending on the important scope boundary. The first sentence is long and parenthetical-heavy, embedding three item types in one clause, which makes it dense on first read but not padded.

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 tool where all six parameters are optional, the description does the essential work of explaining that some addressing scheme must be supplied and that two schemes exist. With no output schema, it also correctly sketches the return shape (page number, verified flag) and the scope boundary. Missing are failure modes for unknown IDs and any note on how the topic's "neighbours" relate, leaving a small but real gap for a zero-required-parameter tool.

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%, so all six parameters are already documented, which sets the baseline at 3. The description does add structural meaning the schema cannot express: that id and the chapter/topic/subject/version combination are alternative addressing paths, and it gives concrete example ID strings. That relationship between parameters is the main value added, but per-parameter syntax is still carried by 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?

"Details for one curriculum item" names a specific resource, and the description enumerates the three ID kinds (chapter, topic like "3.2", objective/worked-example/exercise) with the shape of each result. It does not name the siblings it is distinct from, but the granularity of what each item type returns implicitly separates it from search_curriculum and list_chapters.

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 explains the two invocation modes clearly: pass an nctb: ID, or pass chapter plus optional topic with subject/version. That is invocation guidance rather than selection guidance — no sibling tool is named, and the only implicit exclusion is "Does not return textbook text," which suggests a different tool without pointing to it.

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