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

Annotations only declare it is a non-read, non-destructive, non-idempotent write; the description goes much further with TTL default 90s / max 300s, ready_until_s default 900 / max 7200, meta sanitization and 120-char cap, clear_signal semantics, and the join-now alert fired by status=match_starting. That is substantial behavior beyond structured fields, though it does not say what the call returns or what happens to an existing beacon when re-called with different fields.

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 purpose and WHEN, then defaults, then an example — a sensible order for a dense tool. It is packed tightly with no filler except the 'Credit: Dead Brands' line, which adds no invocation value.

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 12-parameter optional-field tool with an output schema and annotations already present, the description covers the behaviors an agent most needs: TTLs, signal fields, clearing, and the match_starting alert. Remaining omissions (auth via key vs bearer is only in the schema, and no mention of return shape) are minor given the output schema exists.

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 still adds meaning: intro_policy=dnd 'hides from Signal Exchange', ready_until_s defaults and caps, which fields clear_signal wipes, and a concrete example payload. A few parameters (key, area, game, looking) are only covered by the schema, keeping this short of a 5.

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 opening 'Presence heartbeat' plus the WHEN clause states a specific action (announce/publish presence) and names the exact statuses it accepts. It also explicitly contrasts itself with arena_presence_list/count (read) and arena_presence_offline (clear), so an agent can pick it out of the sibling catalog without opening another 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?

WHEN: tells the agent the triggering conditions (heartbeat online/away/looking/match_starting, or publishing a Signal Exchange signal) and the read/clear siblings it should not use instead. 'Re-call before expiry' adds the operational rule that distinguishes a one-shot call from a recurring heartbeat.

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