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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description goes further by enumerating the returned shape (enabled, active, source_url, instructions, knowledge sub-fields, monthly quota with used/limit). It also explains the meaningful semantics of source_url, including that Shopify and WooCommerce catalogs are discovered automatically. It stops short of describing failure modes or what happens when the plan lacks the feature.

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?

The definition is front-loaded with what the agent is and how it behaves, then moves to the returned fields. It is a single dense sentence with a long parenthetical, which is efficient but slightly hard to scan; every clause, including the catalog-discovery note, carries real 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?

With no output schema, the description correctly compensates by listing the returned fields and the quota counters, which is exactly what an agent needs to interpret the response. For a single-parameter read tool this is close to complete, with only error and plan-gating behavior left unstated.

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?

There is a single required parameter, site_id, and the schema already documents it at 100% coverage including the pointer to list_sites. The description adds nothing about the identifier itself, so the schema does all the work and the baseline of 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?

The description clearly identifies the resource as the site's AI agent and explains what that agent does (answers visitors from site knowledge, escalates to the team). It is specific enough to distinguish it from sibling reads like get_conversation or get_channel, though it never names those alternatives explicitly. The title's verb 'Read' supplies the action the prose leaves implicit.

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 only explicit usage guidance is the prerequisite 'paid plans only, see available', which is useful but is a plan gate rather than a when-to-use rule. It implies inspection of the agent's configuration and knowledge state, but never says when to call this versus update_ai_agent or how it relates to sibling read tools. Usage is inferable, not stated.

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