consumer_lag

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

With no annotations provided, the description carries the full burden. It does add useful behavioral context: it defines what 'committed' means and specifically notes that committed = -1 means no offset stored, which is a meaningful edge-case disclosure. However, it doesn't describe read-only safety, pagination, ordering, or what happens if group/topic doesn't exist. For a clearly read-only diagnostic tool, this is adequate but not rich.

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 a tight single sentence stating the metric, scope, and a key edge-case definition. The 'committed = -1' clarification is valuable exactness. Every clause earns its place; no waste. Could be slightly better structured as two sentences for readability but is appropriately concise.

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?

There is an output schema present, so return-value details are handled externally. With no annotations, the description covers the core meaning and the critical -1 edge case. However, for a lag diagnostic tool, it could clarify whether lag is computed per-group+per-topic across all partitions (it does say per-partition), and could note whether it's a live computation or sampled. The absence of annotation safety info is partly mitigated by the clearly diagnostic nature of the tool.

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 0%, so both parameters (group, topic) are completely undocumented in the schema. The description does identify both parameters in its prose ('consumer group on a topic'), which maps group and topic to their roles. However, it doesn't add format, constraint, or behavior details beyond identifying which variables exist. It partially compensates for the 0% 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 clearly states it's a per-partition lag tool for a consumer group on a topic, defining committed offset vs log-end offset. It distinguishes itself reasonably from siblings like cluster_health and topic_audit by focusing specifically on consumer lag, though it doesn't explicitly name a sibling alternative. The verb 'lag' with the resource specifics (consumer group + topic) makes the purpose specific.

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 this is used to inspect lag for a consumer group on a topic (lag matters for replay/consumption delays), and among siblings like replay_readiness this is the direct lag tool. However, there's no explicit when-to-use/when-not-to-use guidance or mention of alternatives. The context of sibling tools suggests distinct purposes, but the description doesn't draw those boundaries.

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