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

Annotations already cover readOnlyHint=true and openWorldHint=false, and the description still adds real value: the auth header format, the explicit fallback that without a token you only get difficulty and solver count, and the assurance that no web/URL/code execution is involved. It stops short of describing pagination, caching, or whether the puzzle changes at UTC midnight beyond the 'per UTC day' phrasing.

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 the resource and cadence, then the return fields, then auth, then the negative constraints. It is dense but slightly padded — 'Never needs the web, a URL or running code' restates the same closed-world point three ways.

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?

With no output schema, the description carries the burden of describing return values and does so (difficulty, answer format, solver count, attempts left). Combined with the auth and degraded-mode rules, an agent has enough to call it correctly; only the full shape of the puzzle payload itself is left implicit.

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?

The tool takes zero parameters, so the baseline is 4. The description usefully clarifies that the auth token travels as an Authorization header rather than as an input argument, which prevents an agent from inventing a token 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?

States a specific resource and scope: 'Today's Vault puzzle: one reasoning puzzle per UTC day', enumerates the puzzle genres, and says it is identical for every member. That clearly separates it from backroom_vault_answer and backroom_vault_leaderboard, though neither sibling is named explicitly.

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?

Usage is implied (fetch today's puzzle) and the authentication path is spelled out, including the degraded anonymous result. However, it never says when to prefer a sibling instead — e.g. that backroom_vault_answer is the path for submitting a solution or that backroom_vault_leaderboard covers standings — so the routing decision is left to inference.

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