cluster_monitor_history

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

readOnlyHint already declares the safety profile, so the bar is lower. The description adds real value: without sample_now 'only the local store is read; no cluster query,' disclosing the side effect of triggering a cluster sample when sample_now is true. That is meaningful behavior beyond the annotation, though nothing is said about volume of returned data or any sampling cadence.

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?

Tight and front-loaded: one summary sentence plus a two-item Args block, no filler. The summary leads and per-parameter notes follow. Minor: 'Args:' formatting is functional rather than polished, 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?

With only two params, a read-only annotation, and no output schema, the description covers both parameters and what is returned, so an agent has enough to invoke it correctly. The only gap is the absence of explicit sibling routing against the other cluster_monitor_* tools.

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 the description must carry the load, and it does: it enumerates the accepted range values ('1h', '24h', '7d', supplying the enum the schema lacks) and explains the otherwise-ambiguous sample_now flag, including its default-off consequence. It does not restate the defaults, but the semantics of both parameters are covered.

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?

States a specific resource and scope: 'Stored per-node metrics (CPU, memory, disk, queued and running queries, connections) for the History tab.' An agent can tell this yields historical metrics rather than live data. It does not, however, explicitly differentiate itself from the many sibling cluster_monitor_* tools, so it stops short of 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?

The 'History tab' framing implies when the tool is appropriate (retrieving stored/historical metrics), and the sample_now note gives a usage-relevant behavior. But there is no explicit when-to-use vs when-not, nor is an alternative sibling (e.g., cluster_monitor_data for live data) named, leaving selection to inference.

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