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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds some genuine behavioral context beyond them: the returned payload contents (decimal strings, source clocks, revision, finality, gaps) and that 'retained-publication restrictions apply' and no new observation is acquired. The restrictions themselves are never defined, keeping this at an adequate-but-shallow level.

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 front-loads a 49-item asset enumeration that duplicates the schema's own enum and consumes the majority of the text, burying the actual behavior. The genuinely informative clauses about clocks, revision, finality and restrictions come after the bloat, inverting the ideal front-loaded structure.

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 tool with no output schema and only 38% schema coverage, the description is too thin. It omits what 'metric' values are valid, what intervals are supported, how sma/smoothing interact, and how publication IDs are chosen, leaving the agent without enough to call it correctly beyond a trivial default case.

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 only 38%, so the description is expected to compensate, yet it explains almost no parameters. It restates the end-exclusive rule and vaguely alludes to interval/publication restrictions but says nothing about metric, sma, smoothing, start, or how interval values are formed, leaving five-plus parameters 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 description states a specific verb+resource ('Read ... observations with decimal strings, original source clocks, revision, finality and gaps'), which tells the agent this returns a time-series of metric data rather than metadata or a list. However, it never distinguishes itself from siblings like fetch_bulk_metrics or get_asset_metrics, so differentiation must be inferred. The core purpose is clear despite the jargon ('unreduced').

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?

There is no explicit when-to-use / when-not guidance and no alternative tool is named, even though fetch_bulk_metrics and get_asset_metrics are obvious candidates. The only implicit usage signal is 'No new observation is acquired', which hints this reads stored data rather than triggering ingestion, but the agent is left to guess when this tool is preferable.

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