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

Annotations only declare readOnlyHint=false and destructiveHint=false; the description adds that 'remove' requires a confirm step and that 'discover' triggers an immediate scan. Those are meaningful behavioral facts beyond the annotations. It does not, however, describe the preview flow that the confirm param references.

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 sentence packs the default, all four actions, and their parameters with no filler. The telegraphic style is slightly compressed but front-loads the essential purpose before the action list.

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 an 8-parameter, multi-action tool with no output schema, the description covers the action space, defaults, and the destructive-path confirmation. It is close to sufficient, with only the return shape and the confirm-preview workflow 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?

Schema description coverage is only 25% (org and confirm), so the description must compensate. It does so by mapping each action to its expected inputs (type/label/url/pageType for add, sourceId for discover and remove), giving semantic shape to otherwise bare parameters. It leaves the relationship between url and type implicit.

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 clear role statement — 'Where Seovyn finds topics' — and enumerates the operations, so an agent knows this is the topic-source registry. It does not explicitly contrast itself with siblings like seovyn_topic_clusters, but the resource (sources) is distinct and unambiguous.

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 specifies the default action ('list'), what each non-default action does, and the precondition for removal ('needs confirm'). It stops short of stating when to reach for this tool versus a sibling, but the intra-tool routing is explicit and actionable.

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