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

readOnlyHint=true already tells the agent this is a safe read, and the description adds real behavioral facts: automatic result truncation to fit context limits, and that data sources are conditional on whether a Prometheus is connected. It says nothing about rate limits, timeouts, or failure modes when a series is absent.

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?

Three dense sentences, front-loaded with the verb and primary use cases before qualifying the data-source conditions. Every sentence carries information, though the long parenthetical series list is heavier than it needs to be for a description.

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?

No output schema exists, but PromQL range results are a well-known matrix shape, so omitting the return format is acceptable. Data-source availability and context truncation — the two behaviors most likely to surprise an agent — are both covered, leaving only minor gaps around failure handling.

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%, so query, duration, step and cluster_id are all self-documented, and the description adds only indirect guidance on what the query string may reference (the ankra_* series). Useful context, but it does not clarify parameter interaction — e.g. how step relates to duration — 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?

States a specific verb and resource — 'Execute a PromQL range query over a time window' — and enumerates the analytic intents it serves (trends, usage over time, restarts in a period, spike detection). The contrast with the sibling query_prometheus (which is cited as the place series are named) makes the range-vs-instant distinction inferable without opening either schema.

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?

Gives clear positive usage contexts (trends, spike detection, restarts over a period) and a valuable routing rule: the platform metrics store answers first, while cAdvisor/kube-state-metrics names only resolve from a Prometheus connected in Cluster Settings > Metrics. It never states the explicit exclusion (e.g. 'use query_prometheus for a single point-in-time value'), so it stops short of a full when/when-not statement.

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