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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds real depth beyond them: what adapter #2 actually does (lists tools, maps join/state/move/rules names, reads rules from tool descriptions), that action=play joins and sends legal moves until the match ends with a cap, and the transport restriction. It stops short of saying whether the connection is persisted locally or how failures/timeouts from the remote server surface, which keeps it off a 5.

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 a 'WHEN:' clause, then scope limits and an example — good ordering with no filler sentences. It is densely parenthetical (adapters, caps, honest-scope disclaimer) and slightly long for a 5-parameter tool, but nearly every clause carries information.

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 an output schema present, return values need no prose, and annotations carry the mutation profile; the description covers scope, auth via key, move cap, and the bounded open-world caveat. The remaining gap is operational: no mention of whether remote failures/timeouts abort the call or how partial discovery results are reported.

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 the baseline is 3; the description still adds value by showing the concrete invocation shape ('{"url":"<url>"}') and by explaining the url→adapter mapping (Dead Brands endpoint vs a generic MCP client) that the schema only states abstractly. The action=play explanation largely mirrors the schema, so it is not a full 5.

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 concrete verb+resource: 'point this arena client at another MCP arena (or re-check ours)', and immediately distinguishes itself from the most confusable sibling ('Differs from arena_join (plays Dead Brands only)'). An agent can identify the tool's job 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?

Opens with an explicit 'WHEN:' clause and names the alternative (arena_join) plus the boundary condition that selects this tool. It also gives explicit anti-scope ('works with MCP arenas that expose join/move style tools... not every third-party server') and transport constraints ('https only; no private hosts'), which is exactly the when-not guidance the dimension asks for.

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