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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. Beyond that, the description discloses the two distinct response shapes and adds a real data caveat — "Some topics have no article yet" — which tells the agent gaps are expected rather than an error. It still says nothing about ordering or identifiers returned, so it is not exhaustive.

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?

It is short and front-loads the resource, with no filler sentences. The trade-off is heavily elliptical grammar ("With a level, the sections of its articles") that forces the reader to reconstruct meaning, costing clarity in exchange for brevity.

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 carries the full burden of describing returns, and it does sketch both modes plus the missing-article caveat. It stops short of saying what each entry actually contains (topic ids, article ids/slugs needed to chain into get_theory), which an agent would need to act on the results.

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 both parameters are already documented and the baseline is 3. The description adds one piece of meaning beyond the schema by explaining that supplying `level` switches the output from a topic inventory to per-article sections; the `lang` parameter gets no treatment, but the schema covers it adequately.

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 precisely — theory articles, one per topic, each split into sections — and distinguishes two result shapes depending on whether a level is supplied. It never names a sibling (get_theory, search_theory, list_levels), so an agent must infer the boundary itself, which keeps it below a 5.

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?

"With a level, the sections of its articles; without, which topics of every level have an article" gives a clear parameter-driven branching rule, which is genuine usage guidance. However, there is no statement of when to prefer this over get_theory (fetch content) or search_theory (find by keyword), so the choice between siblings is left implied.

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