get_time_remaining

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, which the description's [READ] prefix reinforces without contradiction. Beyond annotations, the description adds two valuable behavioral disclosures: the output is structured per dimension (cpu, mem, diskspace) and the crucial 'None does not mean unlimited' warm-up caveat, which prevents a likely misinterpretation. It stops short of 5 by not covering error or edge-case behavior, but the additions are meaningful.

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?

Four sentences, each earning its place: purpose, return structure, sibling routing, and the None caveat. The [READ] tag and primary purpose are front-loaded. Slightly more verbose than strictly necessary, but no wasted 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?

With no output schema, the description correctly carries the burden of explaining return values (per-dimension projected days until full) and covers the warm-up None case. Simple parameters are fully documented in the schema, annotations cover safety, and sibling routing is present. An agent has what it needs 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% — both resource_id ('The resource UUID (typically ClusterComputeResource)') and target ('Aria target name from config; default when omitted') are already documented. The description adds no parameter-level detail beyond the implicit mapping of 'cluster' to resource_id, so the baseline 3 is appropriate.

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+resource ('Predict when a cluster will exhaust its capacity based on usage trends') and names the return value (time_remaining per capacity dimension). It explicitly differentiates from get_capacity_overview ('this tool returns only the projections'), so an agent can distinguish it from siblings without opening schemas. The [READ] prefix also signals operation type.

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?

Provides an explicit routing rule: 'Use get_capacity_overview instead when you also want current headroom — this tool returns only the projections.' This states both the condition and the alternative, leaving no inference needed. The sibling context confirms get_capacity_overview is the right comparison tool.

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