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

Beyond the readOnlyHint annotation, it discloses pagination behavior (20000-character windows, more_text.offset), fuzzy-resolution side effects (the result reports how it was found and what else matched), and an explicit prompt-injection boundary about text being user data rather than instructions. These are exactly the traits structured fields cannot express.

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?

Four sentences, front-loaded with what is returned and then the resolution and pagination mechanics, with the safety caveat correctly placed last. The clause about a word's definition and a tag page's answer is somewhat convoluted, but it carries real information and nothing is redundant.

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 return-value burden itself and does so: it names the fields returned, the more_text marker, and the match-reporting behavior. An agent has everything needed to call it, page through long notes, and handle inexact titles.

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 baseline is 3, and the description adds genuine meaning: `note` accepts an id from any tool's output or a non-exact title resolved by closest-match, and `offset` is explicitly tied to a prior call's more_text.offset rather than being a generic integer. The 20000-character window size quantifies the offset unit.

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?

"Read one entry in full" gives a specific verb plus resource and immediately enumerates the returned payload (whole text as Markdown, tags, folder, dates, plus type-specific extras). This clearly separates it from siblings like list_notes, search_notes, and read_tag, which return collections or different resources.

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?

It establishes the read-one-entry use case and, crucially, prescribes the continuation loop: "when more_text is present, call again with its offset." It also explains that inexact titles fall back to closest-title then content matching, so an agent needn't hunt for an exact id. It never names an alternative tool (e.g., search_notes to locate, list_notes to browse), which keeps it just below the top mark.

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