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

Annotations only flag readOnlyHint=false and no destructive/idempotent hints; the description adds substantial behavior: the 90 s crediting window, the 6 h session cap, the 410 session_gone failure modes (ended/expired/superseded/capped), and the exact auth requirement (SIGN as the player or owner session token). This is well beyond what the annotations 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-loads the core action, then packs cadence, payload, return values, error semantics, and auth into dense, non-redundant sentences. No 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?

Despite no output schema, the description names the return fields (expires_at, playtime_s), specifies the failure path, and covers auth — everything an agent needs to invoke and handle the call correctly.

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 value the schema lacks: state is surfaced on now playing, and session_id is confirmed as coming from start_play. It does not add syntax detail beyond that.

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 — keep a play session alive and credit elapsed time — with the exact crediting cap (90 s). It is clearly distinguishable from siblings start_play, end_play, and now_playing by describing live session maintenance rather than creation, termination, or inspection.

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?

Gives explicit cadence (send every 30 s) and routes the caller to start_play when a 410 session_gone is returned, which is actionable when-to-use guidance. It does not explicitly contrast with agent_heartbeat, though the play-session scoping makes the distinction inferable.

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