rws_metrics_query

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds real value beyond that by disclosing that missing samples remain null and are never interpolated, plus the cursor-based paging contract. It stops short of return shape, ordering, or the 5000-item limit behavior, so a 3 is right.

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?

Two sentences with no filler, front-loaded with the core operation before the paging caveat. Density is high but nothing is wasted; the terseness costs comprehension rather than padding.

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 an 8-parameter, zero-coverage query tool with no output schema, the description leaves most of the calling contract unstated: what the range parameters bound, what runRefs must reference, and what the response contains. The null/interpolation and paging notes cover only a fraction of what an agent needs to call this correctly.

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% across 8 parameters, so the burden falls entirely on the description, and it explains only throughSequence and the null semantics. The bound semantics of fromX/toX ('bounded' is a hint at best), runRefs structure, metricIds filtering, and limit/offset are all left undocumented.

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 verb 'Read' is specific, but the resource 'bounded process series and compatible alignments' is domain jargon and never explains what a 'series' or an 'alignment' is. It does not name or contrast with the obvious siblings rws_metrics_append and rws_metrics_snapshot, leaving the agent to infer that this is the read-side of that trio.

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 only directive is a pagination mechanic ('Reuse throughSequence on every page'), which is a how-to detail rather than guidance on when this tool should be chosen. There is no statement of preconditions, no exclusion, and no reference to the append/snapshot alternatives.

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