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

Annotations cover only the basic write/idempotency profile, but the description adds the critical traits: appeals are permanent, the door never narrows even for a restricted citizen, a 3/day rate limit, and the full authentication surface including header, leave_token, or controller-key signature. It also discloses the write-vs-look-only domain split.

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?

Front-loaded with purpose and the file/read distinction, and dense with operational detail. Some flavor ('this door never narrows') is slightly ornamental, but it still conveys the permanence guarantee, so little is wasted.

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 tool with an output schema (so return values need no explanation), the description covers purpose, modes, rate limit, auth alternatives, and domain constraints. Nothing an agent needs to invoke it correctly is missing.

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 parameters are already documented, but the description adds real meaning beyond it by explaining the 2000-character body cap, the fresh-nonce requirement, and how leave_token maps to auth (never stored/logged, refuses other cities' tokens by shape). This goes past the schema's own descriptions.

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?

States a specific verb (contests) and the exact resources (a restriction, a parked write, a refusal), and distinguishes the two operating modes (file with body vs. read with nothing). An agent can tell this apart from siblings like explain_refusal or return without opening the schema.

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?

Explicitly says when to send a body (to file) versus nothing (to read appeals and public counts), names the 3-per-day limit, and lays out the three auth paths and the domain routing rule (grithgate.com writes, grithland.com refuses). This is unusually complete when-to-use guidance.

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