purge_topic

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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the bar for additional disclosure is lower. The description adds value by specifying the precise scope of destruction — messages are deleted while the topic itself survives — and by disclosing the ownership/prefix requirement. There is no contradiction with the annotations. An explicit 'irreversible' warning is absent, but 'deletes all its messages' combined with the destructive hint conveys the risk adequately.

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?

Three sentences, each with a distinct job: the first states the action and its key nuance (messages gone, topic kept), the second gives the usage workflow, the third states the required precondition. The most important information is front-loaded, and there is no filler or repetition of schema content.

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 destructive tool with an output schema and safety annotations, the essential information is present: what it does, when to use it, and the prerequisite topic ownership. The only notable gap is an explicit 'cannot be undone' warning, though that is largely implied by 'deletes all its messages' and destructiveHint=true. Overall, an agent has enough to select and invoke this tool correctly.

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 100%, so the baseline is 3. The description adds meaning beyond the schema by making explicit the non-obvious ownership eligibility rule: 'The topic name must be one the user owns (starts with their prefix).' This tells the agent to verify ownership before invoking, which the schema's example (u-<hex>.orders) only hints at.

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 specific verb and resource: 'Purge (empty) one of the user's Kafka topics.' It goes further by explicitly stating the scope — 'deletes all its messages but KEEPS the topic' — which differentiates it from the sibling delete_topic without needing to name it. An agent can instantly understand what this tool does and how it differs from the destructive sibling.

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 description gives a concrete when-to-use scenario: 'Use this to restart processing after a mistake: purge, then have consumers read from the start again.' It also adds a precondition — the topic must be one the user owns (starts with their prefix). It does not explicitly name alternatives or state when not to use it, but the 'KEEPS the topic' contrast with delete_topic provides sufficient routing context.

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