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

Translates the readOnlyHint into concrete behavior the agent must rely on: "the platform runs the queries, the model never writes PromQL for a panel." It also discloses failure modes and state semantics the agent cannot infer elsewhere — components outside `fits` are refused, and stale/absent/unknown platform_metrics mean panels render unavailable.

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?

Front-loaded with purpose and precondition, and nearly every clause carries binding-relevant detail (shape→component mapping, parameter binding syntax). It reads as one dense run-on block with deeply nested parentheses, which costs some scannability.

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?

There is no output schema, so the description carries the full burden of explaining return values, and it does — enumerating dataset and cluster fields plus the meaning of each platform_metrics state. Nothing needed to call this zero-parameter read correctly is missing.

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?

No input parameters exist, so the baseline is 4; the description instead spends its effort documenting the returned fields (id, shape, unit, has_capacity, fits, parameters, source) with the meaning of each, which is value beyond the empty 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?

States a specific verb and resource ("List the datasets a canvas dashboard can bind panels to, and the clusters they can be bound for") and immediately distinguishes itself from canvas_present/canvas_patch by positioning itself as the prerequisite step.

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 an explicit call-order rule ("Call it before building or extending a json dashboard with canvas_present or canvas_patch"), naming the two sibling tools that consume its output. It also explains downstream consequences that gate usage, e.g. a component outside a dataset's `fits` is refused and absent platform_metrics should be left out.

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