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

With no annotations, the description carries the full load. It does disclose useful behavioral facts the schema cannot: the tool is 'Free', the drand round refreshes every 3 s, and the score is 'descriptive until 50,000 trials' (a real caveat about statistical validity). It does not state read-only-ness explicitly, message count limits, or freshness of the on-chain anchor.

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 single run-on sentence front-loads identity but wastes words on framing ('an open experiment', 'honest pre-registered', 'the cosmic-bit guessing game') that do not help an agent decide or call. The concrete facts (drand every 3 s, 50,000-trial threshold, free) are buried mid-sentence in a comma pile.

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 must carry the return-value burden, and it partially does by listing the five artifacts returned. But it says nothing about the shape, order, size or limits of 'recent messages', nor how the anchor or score are encoded, which leaves a zero-parameter read tool under-specified for an agent that must consume its output.

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 there is nothing for the description to disambiguate and the baseline of 4 applies. The description's enumeration of returned artifacts is bonus context rather than parameter meaning.

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 never uses a verb – it names 'THE DOOR, an open experiment on Arc' and then lists contents (latest drand round, the word spoken, score, recent messages, on-chain anchor). That contents list implies a state-snapshot read, and it does distinguish the tool from door_glyph / door_guess / door_say, but the agent has to infer 'this returns the current Door state' from marketing copy rather than a stated purpose.

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?

No guidance on when to call this instead of door_glyph, door_guess or door_say. The only hint is 'descriptive until 50,000 trials', which speaks to interpreting the score rather than to tool selection. An agent unfamiliar with the experiment is left to guess that this is the read companion to the door_* action tools.

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