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

The description usefully discloses that 'remove' drops the cluster AND its unwritten keywords and requires confirm, which is exactly the kind of context annotations cannot express. But this squarely contradicts the annotation destructiveHint=false: a tool that deletes clusters and keywords is destructive, so the declared hint actively misleads an agent about the safety of the remove action.

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 that front-loads the resource and then the actions, with zero filler. The parenthetical style is compact to the point of being terse, but nothing is wasted.

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 4-parameter, no-output-schema, multi-action tool the description covers the actions and the destructive/confirm behavior, which is the critical part. It still leaves the return shape of 'list'/'plan', the exact effect of 'plan', and the 'org' parameter unaddressed.

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 only 50%, so the description must compensate. It adds genuine meaning for the 'action' enum values and for 'clusterId' (only relevant to remove) and flags that 'confirm' gates removal, but 'org' is left entirely to the schema and 'plan' is unexplained. It partially, not fully, offsets the coverage 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 description names the resource precisely ('Topic clusters (a pillar keyword and its supporting ones)') and enumerates the three actions it exposes (list/plan/remove), so an agent knows exactly what the tool operates on. It doesn't distinguish itself from the overlapping sibling seovyn_plan, which keeps it from a 5.

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?

Each action carries a short parenthetical that implies when to use it (list is default, plan pulls more from the website, remove drops the cluster and needs confirm), which is real guidance. However, there is no explicit routing against alternatives such as seovyn_plan or seovyn_keyword_targets, so usage is only implied.

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