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

Annotations already declare destructiveHint=true and idempotentHint=true, so the description's added value is the effective partial-merge semantics: unnamed settings and sections are kept, and a duplicate FAQ or form on the same sheet overwrites the first rather than appending. That is exactly the kind of detail an agent cannot infer from the annotation flags. It could go further on ordering or what an empty payload does, but the merge/dedup contract is disclosed.

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?

Three dense sentences, front-loaded with purpose, then merge semantics, then permissions and the confirmation caveat. Every clause carries information, though the middle clause is packed with two distinct rules (keep unnamed, dedupe duplicates) and strains readability slightly.

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 destructive, nested-schema mutation with an output schema present, the agent needs the merge contract, the duplicate rule, the auth requirement, and the confirmation caveat — all of which are given. Residual gaps are minor: section ordering and behavior when no properties are supplied are unstated, but nothing essential to calling it correctly is missing.

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 71% and nested objects already carry descriptions (faq, contact, contactForm, requireLogin, customerRegistration). The description adds meaning at the section level, clarifying that the FAQ section reads questions and answers from a sheet and that the contact form/contact card are distinct portal sections. However, it adds no per-parameter syntax or format guidance beyond what the schema states, so it sits at the baseline-plus level.

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 opens with a specific verb and resource ("Set up the client portal") and immediately enumerates the configurable surface: title, welcome text, sign-in, FAQ, contact form, contact card. That is concrete enough that an agent knows exactly what resource is being mutated. It stops short of naming any sibling (page.update, widget.update, view.publish) to contrast against, so there is no explicit sibling differentiation.

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?

"Owner or an Admin only" and "Always asks the user first" give the agent real preconditions for invoking it, covering authorization and user confirmation. What is missing is when to prefer this over adjacent tools such as page.update or widget.update for non-portal presentation work; the description assumes the agent already knows this tool is only for the customer-facing portal.

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