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

Annotations already declare a destructive write with no open-world reach, so the bar is lower, and the description adds genuinely non-obvious behavior: the copy is deep (sections plus content) and the operation is non-idempotent. It stops short of saying what the response contains (e.g., whether the new page ID is returned) or where the copy is placed.

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?

Two sentences, the operation is stated first and the retry caveat second. Every clause earns its place and nothing is repeated from the annotation or schema.

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 two-param mutation with no output schema, the description covers the risky part (non-idempotency and how to recover) and the copy depth. It leaves open what the caller receives back, which matters for a tool whose whole hazard is a lost response.

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 100%, with both projectId and pageId documented in the schema itself. The description adds no format, constraint, or scoping detail for either parameter, so the schema carries the whole load and the baseline 3 applies.

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?

Uses a specific verb ('Duplicate') with a specific resource ('an existing page') and states the scope of what is copied ('all its sections and content'). The resource noun distinguishes it from duplicate_entry, though it never explicitly contrasts with that sibling or with create_page.

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?

Gives concrete retry guidance: a retry makes another copy, so verify with list_pages when the original response was lost. This is real when-to-use guidance aimed at non-idempotency, but it doesn't cover when to duplicate versus build a new page from scratch.

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