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

Annotations already declare it is a non-read-only, non-destructive, closed-world write. The description adds real behavior beyond them: creation fails on an existing path, and '.md' is auto-appended when the extension is omitted. It does not state what is returned or whether a parent folder must already exist.

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?

Three short sentences, front-loaded with the action, then path format, then collision behavior and the vault-structure pointer. No filler; every clause carries an operational fact.

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?

For a three-parameter write tool with annotations and no output schema, this covers the key risks: path format, extension normalization, and the exists-collision case. Minor gaps remain about path resolution root and whether the response includes the created path.

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 67% – content and change_summary are documented in the schema, path is not. The description compensates by explaining that path includes folders and that '.md' is added if missing, which is genuine meaning beyond the schema's bare string type.

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?

Opens with a specific verb and resource ("Create a new note") and immediately clarifies scope with path semantics and collision behavior. The distinction from append_to_note is implied by "read and append instead" rather than naming the sibling tool, so an agent can differentiate but must infer the mapping.

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?

Gives a clear when-to-use condition plus an explicit when-not: if the path already exists, read and append instead of creating. It also points to vault_overview as the prerequisite for placement conventions, though it does not name append_to_note or read_note directly.

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