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

Annotations already declare readOnly, idempotent, non-destructive and local-only, so the safety profile is covered. The description adds two useful traits beyond them: the return payload is Markdown and one topic is long (a size/cost warning). It still doesn't describe how large the Markdown is or whether it can be fetched repeatedly without cost.

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 sentences, front-loaded with what the tool returns and its access scope, followed by the per-topic triggers. Nothing is wasted, though the quoted topic names and parenthetical are packed tightly enough to be mildly hard 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?

A single-parameter documentation fetch with a full enum schema and no output schema (output is Markdown). The description covers purpose, access, payload format, and when to fetch each topic — nothing an agent needs in order to call it correctly is missing.

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% and both enum values are already documented, so the schema carries the baseline. The description adds decision meaning on top: which operational moment selects "formatting" versus "working", plus the caveat that "working" is long. That is more than restating the enum.

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?

A specific verb and resource ("Read a ThreadPage guide ... as Markdown") with the scope of who can read it ("every level may read it"). It is unmistakably distinct from the CRUD siblings in the list (get_note, get_thread, get_access), which all return workspace data rather than documentation.

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?

Explicit triggers are given per topic: "formatting" before writing tables, checklists, images, files, Note references, or editing a Note; "working" when an error code, a request, or a multi-step edit is unclear. This is genuine when-to-use routing keyed to the enum values, not vague advice.

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