get_resource_metrics

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

Annotations already mark the tool as read-only and idempotent. The description adds meaningful behavioral context beyond annotations: returns a dict keyed by metric key with {timestamp_ms, value} points, explicitly 'not an envelope,' and that keys with no data are omitted from the result. This goes beyond the annotation safety profile.

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 well-structured and front-loaded with the purpose. Each sentence earns its place: the [READ] tag, the return format, the sibling comparison, the missing-key caution, and the Args block with defaults and examples. No filler or redundancy.

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 5 parameters, no output schema, and zero schema descriptions, this description provides complete context: return shape, key omission behavior, parameter defaults, and example metric keys. The only possible omission is error behavior/rate limits, but for a read-only metrics tool this is sufficient for an agent to invoke it 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 0%, so the description carries sole responsibility for parameter semantics. It explains every parameter: resource_id as UUID, metric_keys with concrete examples, hours with default, rollup_type with the allowed aggregation values and default, and target default from config. This fully compensates for the absent schema descriptions.

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 'Fetch time-series metric statistics for a resource' with a specific verb and resource scope. It further distinguishes itself from the sibling tool get_resource_health by explicitly noting this is for history while the sibling is for a single current score.

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 provides explicit use guidance: 'Use this for history; for a single current score use get_resource_health instead.' It also warns about absent keys, telling the agent to check which keys came back before reporting a metric as zero, which is essential for correct interpretation.

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