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

Annotations already cover safety (readOnly=false, destructive=false, idempotent=true, openWorld=false), and the description adds substantial behavior beyond them: registration stores a reference rather than a copy, sender/thread metadata requires an email resource type, account metadata does not authorize provider access, registration does not create a sender/thread association, and permissions are enforced at workspace/project/account scope. The requestId retry guidance clarifies how idempotency works in practice.

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?

Core purpose is front-loaded and the alternative-tool routing follows logically; most sentences carry operational weight. It is dense and slightly sprawling, with some assertions ('Account metadata does not authorize provider access') that read as tacked-on constraints rather than a structured narrative, but no true 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 12-parameter, 3-required mutation tool with no output schema and near-zero schema description coverage, the description supplies the critical context: what gets stored, the namespacing model, idempotency, association limits, and permission scoping. It still leaves several parameters (sourceId, projectId, description, attachment-to-target mechanics) unaddressed, so it is strong but not fully complete.

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 description coverage is only 8%, so the description carries the burden, and it does explain several important parameters conceptually: connectorId/resourceType/externalId namespacing for external identities, sender/threadId requiring an email resource type, requestId uniqueness and reuse, and the version requirement for item targets. However, parameters such as sourceId, projectId, description, and the targetId/attach semantics are not meaningfully explained, leaving a gap that the description does not fully close.

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+resource ('Register a supplied HTTPS link to an existing document, file, or other reference') and immediately clarifies the semantics ('This saves a reference, not a copy of the file'). It explicitly distinguishes itself from two siblings, resource_note and note_append, so an agent can differentiate without opening schemas.

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?

Names the alternative tools and the conditions that select them ('Use resource_note for an editable library note kept in Binder, or note_append for a project/task comment'), which is explicit when-to-use-vs-alternative routing. It also states a prerequisite for updates ('Item updates require the current version from get_tasks, get_items, or get_workspace').

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