Consensus round diagnosis

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so credit goes to added context: votes are "as seen by one node," with a default synced sentry/full node and an override. It also warns that monikers arrive inside <untrusted> tags and must be treated as data — a genuinely useful injection-safety disclosure not expressible in annotations. Missing only limits like rate or freshness caveats for the chosen node.

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?

Front-loads purpose, then use-case, then interpretation, then caveats — a sensible diagnostic order with no filler sentences. It is dense for a single paragraph and would read faster split into short lines, but every clause carries information.

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?

An output schema exists, so return values need not be explained; the description instead supplies what the schema cannot: when to reach for it, how to interpret each named finding, the single-node viewpoint limitation, and the untrusted-content rule. Nothing an agent needs to select or safely call it is absent.

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 100% and the sole parameter is self-documenting, so the baseline is 3. The description adds interpretive value by clarifying that the `node` choice determines whose view of votes you get, which matters for reading the result rather than just passing the argument.

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?

Opens with a specific verb and resource ("Inspect the live consensus round") and enumerates exactly what is surfaced: height, round, step, time at height, arrived prevotes/precommits, and 2/3 voting-power status. That enumeration distinguishes it from siblings like node_status and validator_health, which cannot answer round-level quorum questions.

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?

Gives explicit triggering conditions (chain or node stops producing blocks; stale_head, upgrade_halt) and the two questions it answers ("who is missing?" and "quorum problem or something else?"). It also routes interpretation via named findings (no_quorum, stuck_with_quorum, many_rounds), so the agent can tell when this tool applies versus a general health check.

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