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

Beyond the readOnlyHint and destructiveHint=false annotations, the description discloses pagination limits (at most 20 items), the need to follow nextCursor until null including after short/empty pages, that archived Sites and Topics are excluded while get_site/get_topic still read them, and that clients is only a first-20 preview. These are concrete behavioral traits an agent needs for correct calls. No contradiction with annotations.

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 description is front-loaded with the core purpose and then moves through item structure, routing alternatives, pagination, archive behavior, client preview limits, and exclusions. Every sentence adds operational detail, and no sentence is redundant. It is appropriately sized for the number of edge cases it covers.

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?

Given the rich annotations (readOnly, non-destructive, closed-world) and the presence of an output schema, the description supplies all the invocation-critical context: combined entity discovery, clientId filtering, pagination contract, archive exclusion, and client preview limitation. It does not need to explain return values because the output schema exists, yet it still characterizes the items (id and subjectKind). This is complete for the tool's complexity.

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 description coverage is 0%, so the description must compensate. It explains that optional clientId filters the inventory, which clarifies that parameter. For cursor, it instructs to follow nextCursor until null, implying the pagination token usage, but it does not explicitly map the 'cursor' input parameter to the response's nextCursor or describe its format, leaving a minor gap.

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 first sentence names a specific combined resource (brand Sites and research Topics) and a discovery verb ('Discover accessible'). It also explicitly distinguishes from get_site and get_topic by explaining that shared report/config tools still use siteId for either kind. This lets an agent separate it from its siblings without opening the schema.

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 when to use get_site or get_topic for individual lookups and clarifies that shared report/config tools use siteId for either kind, routing the agent appropriately. It also sets expectations with 'This read does not research, create, edit or launch a scan,' telling the agent what this tool is not for. The optional clientId filter is mentioned as a scoping condition.

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