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

The description says 'Nothing is read or changed,' while the annotations declare readOnlyHint=false, destructiveHint=true, and idempotentHint=false. Those are directly opposing claims about side effects, and an agent cannot tell which to trust. Even though the prose explains the underlying reason (the MCP layer cannot reach the media server), the contradiction with structured fields is disqualifying.

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?

Three short sentences with no waste, and the critical fact (nothing is muted, tool unsupported) is front-loaded after the naming sentence. Each sentence carries distinct information: what it nominally does, why it cannot work, and the net effect. Nothing to cut.

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 stub tool this covers the essential question — can I use this? — with a clear no and a reason. But it leaves the annotation conflict unresolved and names no alternative tool, so an agent trying to actually mute someone is left with nothing actionable.

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?

All six parameters have zero description coverage in the schema, and the description explains none of them — not orgId, roomId, participantId, nor the confirm/idempotencyKey/acknowledgedAmountUsd safety fields. The only implicit guidance is that parameters are moot because nothing executes, which is at least some signal, but the field-level semantics are entirely unaddressed.

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 name pairs a specific verb (mute) with a resource (participant), and the description immediately clarifies that the operation is a mediasoup host command that this server cannot actually execute. An agent reading it knows both the nominal purpose and the real-world status, which effectively distinguishes it from working siblings like list_participants or end_call. It stops short of 5 only because it never names a working alternative.

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?

The description gives an unambiguous when-NOT-to-use signal: 'This tool is not yet supported. Nothing is read or changed.' An agent should never invoke it, and that is stated plainly. However, it offers no redirection to a sibling tool that could accomplish muting, which is the missing piece for a top score.

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