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

Annotations already mark this as non-read-only and non-idempotent; the description adds the essential trait that fetching consumes and deletes the messages, which is the key behavior an agent must know. The only weak point is that deletion is disclosed while destructiveHint is false, creating a mild tension, and nothing is said about empty-result or pagination behavior.

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?

Two short sentences, front-loaded with the consuming fetch semantics. The trailing wait clause largely duplicates the schema's own description, so it is not fully waste-free, but nothing is bloated.

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 should say something about what comes back (a list of signaling payloads, ordering, behavior when nothing is waiting). It covers the deletion side effect but leaves the return shape entirely 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?

Schema coverage is 100%, so both parameters are already documented. The description restates the wait semantics (long-poll, max 20) without adding anything the schema lacks, and never mentions agent_key, which the schema handles. Baseline 3 is appropriate.

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 names a specific verb and resource: 'Fetch (and delete) signaling messages addressed to you.' The parenthetical clarifies consumption semantics, and 'signals' distinguishes it from inbox/message readers. It does not explicitly contrast with siblings like read_inbox or catch_up, so it stops short of a 5.

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?

There is no when-to-use or when-not-to-use guidance. The agent is left to infer from 'addressed to you' that this is the channel for WebRTC signaling rather than general messaging, and nothing routes it away from read_messages or catch_up.

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