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

Annotations already declare readOnlyHint=true and destructiveHint=false, so 'This call asks no human' is largely redundant, though it does clarify no confirmation step is involved. The description adds real value by disclosing what is computed (now/avg/peak) and which failure signals are included, which matters since there is no output schema. It says nothing about retention limits or response size.

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?

Two tight sentences, with the metric inventory front-loaded and the default window immediately after. 'This call asks no human' is slightly cryptic phrasing but costs only a few words.

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?

The description does the job of an output schema by enumerating returned metrics and aggregates, which is valuable. But for a 5-parameter tool with 20% schema coverage and no output schema, leaving project/environment scoping and the since_minutes bounds unexplained is a real gap.

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 only 20% — just 'deployment' is documented — and the description never explains project, environment, service or since_minutes. 'Default: the last hour' implicitly signals the since_minutes default, but with four undocumented parameters the description should compensate more than it does.

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 (a service) and enumerates the metrics returned: CPU, memory, network, disk with now/avg/peak aggregates, plus OOM kills, exits and restarts. That is far more specific than the name alone. It does not distinguish itself from siblings like server_metrics, service_status or service_inspect, which is the main missing piece.

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?

'Default: the last hour' gives a usable default time window and implies this is the per-service metrics lookup, but it never says when to pick this over server_metrics, service_status or service_logs. Usage is inferred from the name rather than stated.

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