Read buffered WebSocket frames

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

Goes well past the annotations: newest-first ordering, limit capping, the buffer-emptying side effect of clear=true, the getgenv/registry guard, and the {error} fallback for unknown ids. The one unreconciled point is that clear=true mutates the ring while readOnlyHint=true and destructiveHint=false are declared; the description discloses this, so it is context rather than a contradiction, but the tension is left for the agent to resolve.

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 prose opening is dense and front-loaded with the important facts, but the trailing block (Phase/cost/idempotency/Requires/Capabilities/Produces/Safety) duplicates annotation data and the Signature line repeats the schema, padding a description that was already complete.

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 return contract itself ({ id, open, messageCount, messages } or { error }) plus the guard and clearing semantics, which is sufficient for correct invocation. It defers exact field details to tool-schema, a minor gap rather than a missing requirement.

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, but the description adds real meaning: it states that results are newest-first, that clear acts after the snapshot, and that threadContext is optional/omit-for-default. The signature line largely restates the schema rather than extending it.

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 verb (read) and resource (inbound frames buffered for a WebSocket) and scopes it by registry id from ws-connect. An agent can distinguish it from ws-list, ws-connect, ws-send, and ws-close without opening any 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?

Clearly implies the prerequisite (a socket opened with ws-connect) and explains the key usage decision — clear=true empties the ring so subsequent calls only see newer frames. No explicit when-not or named alternative, but the operating context is unambiguous.

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