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

Annotations already mark idempotentHint=true and destructiveHint=false; the description adds genuinely useful behavior by explaining the upsert semantics ('create or replace'), the optimistic concurrency guard ('refuse overwriting a newer edit'), and that content is Markdown. No contradiction with annotations.

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 sentences each earn their place: the core action, the concurrency behavior, and the content format. It is front-loaded and free of filler.

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 7-parameter write tool with no output schema, it covers the action, scoping, concurrency, and body format; the schema handles key, kind, scope, and teamId. It is complete enough for correct invocation, though a one-line note on what the call returns would have been helpful.

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?

With schema coverage at 57%, the description compensates for the two undocumented parameters: expectedRevision is tied to notes.get and overwrite protection, and content is defined as the full Markdown body. Only title lacks any explanation, but it is a minor optional metadata field.

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 opens with 'Create or replace a note,' specifying both the action and the resource, and scopes it to 'the key owner's account or in a team.' This clearly differentiates it from the read-only siblings notes.get and notes.list.

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 implies write usage by using 'create or replace' and tells the agent to source expectedRevision from notes.get, which is a concrete tie to an alternative. It does not explicitly state exclusions, but the write-vs-read split is clear enough given the sibling set.

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