replay_readiness

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

With no annotations provided and an output schema present, the description carries the full disclosure burden. It explains the question being asked but doesn't disclose behavioral details: whether it's read-only, whether it queries brokers/admin servers, whether it considers compaction vs. deletion retention, or what edge cases exist (e.g., compacted topics). The output schema exists but the description doesn't define what values/tags the tool returns to answer the readiness question.

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 extremely short - a single question. It's front-loaded and wastes no words, but it's under-specified rather than optimally concise. A well-crafted description could add behavioral and output detail in 2-3 sentences without losing the brevity.

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 there's an output schema but no annotations, the description should at least clarify the tool's behavior and return semantics. It doesn't explain what the readiness answer looks like, what thresholds matter, or how retention deletion is determined. For a tool with a nuanced Kafka concept (replayability vs retention vs offsets), the description is too thin to fully guide an agent.

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 0%, so the description must compensate for what group and topic mean in this context. The description implies group is a consumer group and topic is the Kafka topic, but doesn't add meaning beyond their names/titles. It doesn't clarify required format, whether the topic is the source topic being replayed from, or any relationship between the two parameters beyond both being inputs.

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 tells you the tool checks whether a group can replay everything since committed offsets or if retention has deleted part of the gap. It names the resource (group+topic) and the question being answered. However, it doesn't state what the tool outputs (a boolean? a percentage? a message?) and doesn't use a verb like 'check' or 'evaluate' explicitly; it's phrased as a question rather than an action. The description is reasonably distinct from siblings like consumer_lag and topic_audit, though it doesn't explicitly differentiate.

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 implies usage for assessing replay capability, which involves retention and committed offsets context. It gives a clear scenario where the tool applies. However, it doesn't contrast with alternatives or state when NOT to use it, and doesn't mention whether this should be used alongside consumer_lag or topic_audit for a fuller picture.

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