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

Annotations already declare destructive=true, idempotent=true, and openWorld=true. The description adds a genuinely non-obvious behavioral note — that app-only execution prevents model context disclosure while the host still sees requests. However, it never clarifies which of the six actions are reads versus writes, so the destructive flag's applicability per action remains opaque.

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?

The text is short, but the first sentence is a comma-spliced fragment list rather than a front-loaded statement of function, and the second sentence's app-only/host remark is tangential to invoking the tool correctly. Size is fine; structure and load-bearing value are weak.

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?

This is a high-complexity tool: six actions, a nested patch object, two required parameters, zero schema descriptions, and no output schema. The description omits action-specific behavior, conditional parameter requirements, and mutation semantics, leaving substantial gaps an agent must fill by guessing.

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 0%, so the description must carry the burden, and it largely does not. It hints at reader controls, activity/leads, and alerts, which gesture at the action enum, but says nothing about id, patch (passcode, expiresAt, captureFields), cursor, or enabled, nor which parameters apply to which action. Two required parameters are effectively undocumented.

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 names the domains the tool covers (reader controls, activity/leads, alert preferences), which loosely maps to the action enum, but it never states a verb+resource and reads as a fragment list. It also fails to distinguish this tool from siblings like get_document_activity, get_document_leads, get_document_alerts, get_document_reader_settings, and update_document_alerts, which cover the same ground. An agent cannot tell from the text how this differs from those.

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?

There is no explicit when-to-use guidance and no alternatives are named, despite at least six sibling tools overlapping with these actions. The only quasi-contextual statement is about app-only execution, which is not a use-selection criterion. The agent is left to infer trigger conditions entirely.

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