Grafana: Query Prometheus

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

Annotations only declare readOnly/openWorld, and the description goes well beyond them: it discloses the return shape (min/max/avg/last per series, one value per step on a shared grid, null where no sample), the `common_labels` de-duplication, and relative payload cost ('about a tenth of the size'). That cost/shape guidance is exactly what an agent needs to avoid token blowups.

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?

Four sentences, front-loaded with the default mode and the 'almost every question' heuristic, then progressive detail on range/stats and aggregation. No filler and no restatement of the tool name or title.

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?

For a 12-parameter tool with no output schema and thin annotations, the description covers mode choice, output shape, payload size, and aggregation strategy — enough to call it correctly. It says nothing about failure modes (bad PromQL, missing datasource) or what an empty result looks like, which is the remaining 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 100%, so baseline is 3; the description adds genuine meaning on top by explaining the mode tradeoff, the view+sort interaction for outlier hunting, and the step/scrape-interval floor. It reinforces rather than repeats parameter docs, though per-parameter edge cases (limit vs topk interplay, precision) are left mostly to the schema.

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?

Specific verb + resource: 'Evaluate PromQL through a Prometheus datasource', which cleanly separates it from the LogQL sibling grafana_query_loki and from panel/search tools. It also states the two operating modes up front, so an agent knows the shape of the call before opening the 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 explicit decision rules: instant is 'the right mode for almost every question', range is for shape-over-time, and 'use view=stats with sort=max to find outliers among many series'. It also states an anti-pattern ('Aggregate in the expression ... rather than fetching raw series'). It stops short of naming tool-level alternatives (grafana_query_loki, grafana_run_panel_query), which keeps it from a 5.

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