instant_query

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the return envelope ('returned'/'limit'/'truncated') and warns that a truncated result is partial, advising the user to narrow the selector or raise the limit. The prefix '[READ]' also signals a read-only operation, adding transparency beyond the schema. However, it doesn't detail error behavior or permission requirements, which keeps it from a perfect score.

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 and well-structured, starting with a clear one-liner, followed by an Args block, and a Returns note. Each sentence provides essential information without fluff. The formatting is easily scannable for an AI agent, making it highly efficient.

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?

Given the tool's simplicity (3 parameters, no output schema), the description is complete. It covers the purpose, all parameters with examples, the return envelope, and the critical truncation edge case. There is no output schema to rely on, so the description adequately explains what the agent will receive. The only minor omission is explicit inter-tool guidance, but that is not required for 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 description coverage is 0%, so the description must fully compensate. It does exactly that by explaining each parameter: query with examples ('up' or 'rate(http_requests_total[5m])'), time as 'Optional RFC-3339 or unix timestamp,' and target as 'Prometheus target name from config; omit for the default.' This adds meaningful semantics beyond the bare schema types and titles.

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 'Evaluate a PromQL expression at a single instant,' which is a specific verb (evaluate) plus resource (PromQL expression) and scope (single instant). This clearly distinguishes it from range query tools in the sibling list, such as 'range_query', by emphasizing the instant evaluation point. The inclusion of example queries further clarifies the intended operation.

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 clear context by specifying 'at a single instant,' which signals when this tool is appropriate (instant queries) versus range queries. However, it does not explicitly name alternative tools or state when not to use it, such as mentioning 'use range_query for time-series over a window.' This nuance prevents a 5 but the context is sufficiently clear.

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