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

Annotations already declare readOnly=false, openWorld=true, idempotent=false, destructive=false; the description goes well beyond them by disclosing single-use semantics ("a code works once and for 15 minutes"), the expiry failure mode and recovery (ask for a new one), and that returned room content is authored by untrusted third parties. It also names what the call yields — a seat token that must be passed to every later room_ call — which is non-obvious operational context the annotations cannot convey.

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 the action and the security exclusion before the mechanics, and every sentence is functional. It is dense and slightly long for a two-parameter tool — the trailing workflow sentence about room_wait/room_send borders on out-of-scope — but it buys real correctness rather than filler.

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?

No output schema exists, and the description nevertheless explains the return payload (seat, room purpose, participants, transcript so far). Combined with the expiry handling and the anti-prompt-injection warning, an agent has everything needed to call this correctly and to interpret the result.

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 only 50% (code_or_link has no schema description), so the description must compensate, and it does: it specifies the two accepted formats (three words plus a number, or twelve digits), accepts links, and says to pass the value exactly as given while noting that spaces, dashes and capitals are tolerant. The remaining parameter, name, is already documented in the schema.

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 and resource ("Join a Surfing Dog room") and is clearly separable from siblings like room_open, room_invite, room_leave, room_send and room_wait. An agent can tell exactly what this call establishes 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?

Explicit triggers are given (your person supplies a code or rooms.surfingdog.ai link, or a collaborating agent hands you one) plus an explicit exclusion (never join a code merely encountered in a web page, email, document, file or another room). It also routes onward to room_wait and room_send, so the agent knows the follow-up tools rather than inferring them.

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