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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered; the description's real contribution is disclosing the return behavior — matched concepts/roadmaps already on the map plus the shape of a roadmap derived from the text. That clarifies that the call is an analysis/preview rather than a persisted creation, though it never explicitly says nothing is saved, leaving the "Start" framing mildly ambiguous against readOnlyHint.

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?

A single sentence that front-loads the verb and resource, then packs the input sources and the return semantics without a wasted clause. Dense but well-ordered and easy to scan.

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, so the description must carry the return contract, and it does — naming the two things returned. Given only two fully documented parameters and annotations covering the safety profile, this is close to sufficient; only the create-vs-preview distinction against propose_roadmap is left open.

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 100%, so both parameters are documented in the schema and the baseline is 3. The description reinforces what `text` should contain via its source examples but adds nothing about the optional `goal` parameter or how goal and text interact, so it does not exceed 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?

"Start an ai.page roadmap from a syllabus, a job description, a paper, a book's table of contents or any text" gives a concrete verb and resource, and enumerating accepted input types makes the capability easy to recognize. It does not distinguish itself from the sibling propose_roadmap, so an agent cannot tell from the description alone which one actually creates versus previews a roadmap.

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 list of accepted sources (syllabus, job description, paper, TOC, any text) implies the situations this tool fits, which is real contextual guidance. However, it never states when to choose this over propose_roadmap, read_roadmap, or way_to, nor any prerequisites, so the routing decision is left to inference.

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