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

Annotations already declare readOnly, idempotent, non-destructive behavior, so the safety bar is met. The description adds genuinely new context: results are session-scoped and deliberately exclude storage keys and employee data, which tells the agent what it will and won't get back. It stops short of noting pagination or result limits.

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 with zero filler, leading with the operation and scope. Every sentence carries distinct information (scope, follow-up usage, output exclusions).

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?

An output schema exists so return structure needn't be described, and the description appropriately focuses on what is omitted from results. For a single-parameter read tool with rich annotations, the only real gap is sessionToken sourcing and any result-size behavior.

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 one parameter at 0% schema description coverage, the description must compensate. It hints that sessionToken is an email-verified session token, but gives no format, source, or lifecycle detail for the value. The documentId reference is a return-field hint, not a parameter explanation.

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 (List) and resource (document metadata) with an explicit scope: 'owned by the email-verified request session'. This scope sentence distinguishes it from siblings like applications.get_document, which retrieves a single document by ID.

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 explains the downstream workflow ('Use documentId with applications.get_document or applications.remove_document'), which implies this is the entry point for discovery. However, it never states when to call this versus other listing/status siblings (e.g., applications.get_status) or any precondition for the session token beyond it being verified.

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