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

Annotations only cover the safety profile (readOnly, idempotent, closed-world, non-destructive); the description adds substantial behavior beyond that — per-layer licence outcomes, the share-alike overhead on composite layers, and explicit degradation rules (omitted url is dropped and named in `omitted`, missing as_of yields RETRIEVED instead of a data date, missing layer yields a scoped statement rather than a grant). This is exactly the kind of conditional-failure disclosure annotations cannot carry.

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?

It is front-loaded correctly — the trigger and the deliverable come first, licence detail second. But it is a single dense wall of text with all-caps emphasis, a star marker, and an inline URL, and it restates the return object's fields even though an output schema exists. The licence explanation earns its space; the parenthetical length and repeated framing ('LICENCE IS PER LAYER AND THIS IS THE POINT') could be tightened considerably.

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 five-parameter, zero-required, output-schema-backed tool, an agent has everything needed: when to call, what to pass, what happens on each omission, and what the licence outcome will be. The only supplementary pointer (data-sources terms) is given as a URL rather than assumed knowledge.

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 the baseline is 3, but the description adds meaning beyond the field docs: it frames url/as_of/completeness as values lifted from the cited response, and explains that layer is the switch that selects the licence line rather than just naming the field. The licence consequences per layer value (CC-BY-4.0 grant vs. upstream-terms pointer) are the real payload and only appear here.

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 opening clause gives a specific verb and deliverable — 'returns one paste-ready attribution line for the value you are about to cite' — plus the trigger condition ('when you quote a DC Hub data center or power figure'). This is unmistakably distinct from every sibling tool, which fetches data rather than formatting attribution.

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 trigger is explicit and actionable: use it when quoting a figure, and pass the values read off the cited response. It does not name a when-not case or an alternative, but no sibling performs this function, so the routing risk is low. A short negative case (e.g. don't use for internal notes) would push it to a 5.

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