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

Beyond the readOnly/openWorld annotations it discloses the permission scope required, the fallback result (title and link only), the meaning of the `truncated` flag and the obligation to say so, and an explicit prompt-injection instruction. That is exactly the behavioral context annotations cannot carry.

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?

Five short sentences, each carrying a distinct rule: capability, permission gate, truncation handling, injection warning, agent_name, safety. Nothing is repeated from the annotations and the capability statement is front-loaded.

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?

With an output schema present the description rightly skips return-value enumeration, and it covers the auth gate and safety posture an agent needs. It is still thin on how to obtain a pageId/connectionId and what the two unrelated id parameters scope.

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 only 25% and the description compensates for just part of it: `agentName` is called out explicitly and the page/database target is implied. `companyId` and the nested `connectionId` UUID wrapper are left entirely to the bare schema, so half the inputs remain semantically opaque.

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?

"Reads one Notion page as plain text, or one database as a line per row" gives a specific verb and resource plus output shape, which clearly distinguishes it from list/search style siblings. It stops short of naming the alternative siblings (connection_search_connected_pages, connection_get_connected_file/thread/transcript) that an agent might confuse it with.

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 states a concrete prerequisite (the connection needs read_body) and the degraded behavior without it, which tells the agent when the call is worth making. It never routes the agent to a sibling when the id is unknown, nor says when not to use this tool.

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