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

Rich disclosure beyond the annotations: one read credit consumed, only usage metadata persisted (never page content), private content is forwarded to the AI and may persist in chat, and explicit prohibitions on writes/posting/impersonation/compiling people's data. This also usefully reconciles readOnlyHint=false (history metadata is written) with the "no writes" claim, so nothing is contradicted. However, it never describes what the call returns or what a failed fetch looks like, which is the remaining behavioral gap.

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?

Front-loaded with the action and its account constraint, then layers precondition, quota, privacy, and prohibition clauses in a sensible order. It is dense and reads as several policies packed into one paragraph, but almost every sentence carries operative information.

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-parameter read tool with no output schema, the definition covers invocation constraints, credit cost, privacy consequences, credential handling, and the failure/retry path — enough for an agent to call it safely. The missing piece is return-shape and off-host error behavior, minor since no output schema exists to lean on.

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 0%, so the description carries the full burden and does add meaning: account_id is one of the user's connections (discoverable via `list_connected_accounts`), and `link` must resolve to the connected host with www variants tolerated. It still does not specify link format (full URL vs bare path) or what happens when a link is off-host — accepted, or error?

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 and resource ("Read a page") plus the distinguishing scope qualifier: it uses a connected website account the user explicitly chose, with account_id identifying one of the user's connections. That implicitly separates it from the anonymous `read`/`read_site`/`see_page` siblings, but it never names them, so an agent must infer the boundary.

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 real preconditions: the connection must be enabled for AI access and the link must be on that connection's host (www variants accepted), plus a fallback path when a sign-in/MFA/bot wall is hit. It does not explicitly say when to prefer the plain `read` sibling instead, which is the main gap for a tool family this dense.

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