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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the tool is known to be safe. The description adds behavioral context: the warning that broad queries return unhelpful results and the detail that filterCel supports == null for unlabelled dimension values, which goes beyond the schema.

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 compact: two sentences plus an example. It is front-loaded with the core purpose, followed by usage guidance and a clarifying example. No wasted 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 tool has no output schema, but the description covers what it does, when to use it, and includes an example. It does not detail the return format, but for a suggestion tool with no output schema this is acceptable. The annotations and sibling context provide enough completeness.

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%, but the description adds meaningful value by providing an example filterCel value ("cos_provider in [\"GCP\"]") and explaining the == null syntax for unlabelled dimension values. This enriches the parameter semantics beyond the schema alone.

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 uses a specific verb 'Suggest' and resource 'usage metric units' with concrete examples (k8s_cpu_hours, network_bytes_out) to analyze in the current billing context. It clearly differentiates from sibling tools like suggest_actions or suggest_groupby by focusing on metric units in billing context.

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 explicitly states when to use ('Only use when a specific filterCel scope is provided') and warns against broad queries ('broad queries will return unhelpful results'). It does not name alternatives, but the condition is clear and actionable, with an example.

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