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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the lower bar applies. The description still contributes real context beyond them: list page size (30 at a time), name ordering for the list, and that roadmaps can nest other roadmaps in the detail payload.

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 dense but purposeful clauses, front-loaded with the primary payload and then the fallback list mode; no filler. The telegraphic style ('A roadmap as Markdown: its sections...') is slightly fragmentary but readable.

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?

There is no output schema, and the description does the work of describing both return shapes, including ordering and page size. Paging continuation semantics and what 'ready to learn' means operationally are the only gaps, and the schema covers offset.

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 the schema already documents q, offset, and roadmap including the 'leave out for the list' note. The description only restates that q narrows the list and only lightly implies offset continuation via '30 at a time', adding little beyond the structured fields.

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 delineates two modes: with an id it returns a roadmap rendered as Markdown (sections, ordered concepts, included sub-roadmaps, learnable items); without an id it returns a name-ordered list. That is a specific resource plus a specific payload, though it never names a sibling it might be confused with (read_concept, way_to).

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 'with an id / without an id' framing effectively tells the agent which mode to pick and what each yields, which is the key usage decision here. It stops short of explicit exclusions or pointing to alternative tools for adjacent needs, so it falls below the top band.

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