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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuinely new behavioral context beyond them: that this proxies GET /api/physics without opening a URL, and the temporal rule that a roll's recompute secret is only disclosed after its UTC day ends. That timing behavior is the kind of trait annotations cannot express.

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 primary purpose is front-loaded in the first sentence, and the conditional roll_id mode follows in a second. It is appropriately sized, though phrases like 'through this connector' and 'without requiring the host to open that URL' are slightly redundant meta-commentary that could be tightened.

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 must describe returns — and it does, enumerating inputs, day fingerprint, pre-day publicness, and post-day secret. The dual global/per-roll behavior is covered. What is left unstated is response shape details for the no-roll_id case beyond a list of fields, keeping it just short of fully complete.

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 100%, so the roll_id format ('one public roll id from a chance_rolled event, a room settle, or an action answer') is already documented, setting a baseline of 3. The description adds meaning above the schema by framing roll_id as selecting a 'roll or random pick' and by explaining that the whole response shape changes depending on whether it is supplied.

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 names a specific verb (read) and concrete resources: the frozen mechanism vocabulary, ability fields/defaults, enforced limits, and — with roll_id — one public roll including its inputs, day fingerprint, and reveal secret. That is far more than a restatement of the name 'physics'. It does not, however, differentiate itself from plausible siblings such as 'laws' or 'official_facts', so it stops short of a 5.

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?

It gives a clear usage trigger — call it 'before relying on' the mechanism vocabulary or limits — and explains the conditional mode: supply roll_id to inspect a single roll instead of the global physics. It offers no when-not guidance and only names an alternative ('Lost? Call front_door') for a meta situation, so there are no explicit exclusions.

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