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

Far beyond the annotations, it enumerates exactly what survives the copy (title, markdown content, emoji/link icon and cover, schema-accepted properties) and exactly what does not (comments, page history, permissions, Notion-hosted files, non-markdown blocks), plus the caveat that markdown rendering can alter block formatting. Annotations only say readOnlyHint=false and destructiveHint=true; the description supplies the real behavioral contract, including the return payload, without asserting anything read-only.

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?

Purpose is front-loaded in the first clause, followed by the copy contract, the omissions, and finally return values, which is the right order for an agent deciding then invoking. It is dense but every clause carries distinct information; the only soft cost is that the returns are packed into one long trailing sentence rather than a short enumerated list.

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 mutating, partial-fidelity copy operation with no output schema and five parameters, the description covers initiation, fidelity limits, failure-adjacent signals (unknown_block_ids, properties_not_copied) and truncation. An agent can decide, invoke, and interpret the response without consulting anything else.

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%, so the baseline would be 3, but the description adds meaning the schema does not: it clarifies that page_id is the source of the read step, that data-source placement filters properties by the target schema, and that the title/icon/cover are inherited unless overridden. It does not spell out the exactly-one-of constraint on parent_page_id/parent_data_source_id (the schema does), so it falls just short of a 5.

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?

"Copies one Notion page under a parent page or into a data source" states a specific verb, resource and destination, and the clause "Notion's API has no duplicate" explains why this exists rather than notion_create_page. It never names the sibling it supersedes, so the agent must infer the boundary from the read-then-create mechanics, but the operation itself is unambiguous.

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?

The description makes clear this is the path for cloning an existing page and that the target must be either a parent page or a data source ("in a data source, the property values the target schema accepts"), which effectively explains both modes. What it lacks is an explicit exclusion such as "use notion_create_page for a brand-new empty page" or a note that the source must be readable by the connected account.

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