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

Annotations cover the safety profile (readOnly=false, destructive=true, idempotent=true, openWorld=true), and the description still adds substantial context beyond them: entries are permanent, may trigger email notifications and subscribed MCP event callbacks, the server assigns attribution so callers cannot self-assign, and corrections append rather than overwrite. It also explains the idempotency contract for requestId and the source-dedup behavior ('that comment is returned, marked existing').

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?

Dense but well front-loaded: the core action and its sibling distinction come first, followed by behavioral caveats. Every sentence carries information, though the run-on paragraph packs routing, auth, idempotency and versioning together with little visual separation, which slightly hurts scannability.

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 mutation with no output schema, it covers permanence, notifications, attribution, dedup-on-source, idempotency and permissions. It leaves mentionedUserIds semantics and the maxLength on body unaddressed, and does not say what the call returns on success.

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 only 29%, so the description has to carry weight, and it does for requestId (unique, reuse on retry), source (system, ID, original author, time for imported history), replyToId (replies require notes:read) and correctionOfId (append-only correction). It adds no meaning for mentionedUserIds or the body length constraints, which is the remaining gap.

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?

States a specific verb and resource ('Append a permanent project or task comment') plus the use cases (update, decision, imported history). It actively distinguishes itself from two siblings by name — resource_note for editable library notes and notes_append for bulk additions — so an agent can route without opening another schema.

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 routing rules: use resource_note for editable notes, notes_append to add many, and item updates require the current version from get_tasks/get_items/get_workspace. It also states prerequisites (notes:read for replies and corrections) and the retry condition for requestId.

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