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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, but the description adds real behavioral context: 'This read does not change setup or launch a scan' and the ID-refusal rule. The null-handling semantics ('strategicGoal strategy note (null when absent)'; 'null focus means equal treatment') are genuinely useful beyond what annotations convey.

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?

A single dense paragraph, front-loaded with the core action and source of the ID. The enumeration of returned fields (title, description, topicProfile, etc.) is somewhat redundant since an output schema exists, but the sentences are information-dense with little filler.

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 single-parameter read with an output schema and read-only annotations, the description covers sourcing, exclusions, and non-mutation behavior adequately. It over-explains return values that the output schema already provides, and omits any statement about error behavior or access requirements, keeping it just short of a 5.

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?

With only one parameter at 0% schema description coverage, the description must carry the load, and it does: topicId is sourced from list_sites_and_topics (subjectKind=topic), must be a topic rather than a brand Site ID, and is the same ID used as siteId by report/config tools. It doesn't restate the UUID format, but the schema handles that.

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?

Specific verb+resource ('Read one research Topic by topicId') with the exact source tool named ('list_sites_and_topics with subjectKind=topic'). It also implicitly separates itself from get_site by noting that a brand Site ID is refused, so an agent can distinguish it from the neighboring read tools.

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?

Tells the agent where the topicId comes from (list_sites_and_topics with subjectKind=topic) and gives an explicit exclusion ('A brand Site ID is refused'). It also notes that shared report/config tools reuse this ID as siteId, which aids correct invocation. It stops short of naming get_site as the alternative for site reads, so not quite a 5.

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