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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds context: it returns the exact same response as GET /api/physics, and explains what happens with roll_id (reads one public roll, its inputs, day fingerprint, public-before-day status, and the secret after UTC day ends). This adds meaningful behavioral detail beyond annotations.

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 is moderately sized and front-loaded with the main purpose. It includes useful details about roll_id behavior and the alternative front_door tool. The 'Lost?' sentence is slightly extra but provides helpful routing. No wasted words, though it could be slightly tighter.

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 read-only tool with no output schema, the description explains what it returns (same as GET /api/physics) and the roll_id behavior. It also points to /api/tools for full catalog and front_door for the city front door. It doesn't describe the exact response structure, but since it says it's identical to GET /api/physics, that's acceptable. Annotations cover safety.

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 schema already documents roll_id. The description adds context about what roll_id refers to ('one public roll id from a chance_rolled event, a room settle, or an action answer') and what reading it returns, which is useful. Baseline 3 is appropriate since the schema covers the parameter.

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 ('Read') and resource ('city physics'), and clarifies it returns the same response as GET /api/physics. It distinguishes itself from siblings by naming front_door as the alternative for reading the city front door, though it doesn't explicitly contrast with all siblings.

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 clear context: use it to read frozen mechanism vocabulary, ability fields, defaults, and safety ceilings before relying on them. It also says to use front_door for the city front door, providing an alternative. It doesn't explicitly say when not to use it, but the context is clear enough.

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