Watch a coin (webhook)

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

Annotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=true, and destructiveHint=false; the description goes far beyond that by disclosing the polling cadence, the exact event triggers (verdict word change, dev sold, liquidity pulled, wallets dumping), that the initial read emits no event, and the HMAC signature header format. It also surfaces the operational prerequisites an agent would otherwise miss: a required Toll key and a per-tier subscription cap (3 / 20 / 50 / 100 by $TOLL held).

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?

It is a single dense paragraph, but front-loaded correctly: purpose first, then event semantics, then return values, then prerequisites. Nearly every clause carries information an agent needs; only the closing tagline 'Facts, not advice' is padding that could be cut without loss.

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 available, the description takes on the full burden and discharges it: it states the return values (watch id, and the one-time signing secret), documents the signature header format, and explains the delivery contract. Combined with auth requirements and tier caps, an agent has everything needed to call this correctly on the first attempt.

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 description coverage is 100% – address and url are both documented with pattern and format constraints – so the schema already carries parameter meaning and a baseline 3 applies. The description adds only light reinforcement ('your https url', 'one ... coin'), and it does not restate the 0x/40-hex address requirement or the maxLength of 300 that the schema supplies.

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 opens with a specific verb and resource ('Watch one Robinhood Chain coin for your agent') and immediately explains that this is a recurring webhook subscription rather than a one-off read. It distinguishes itself in substance from check_coin/check_coins (one-shot reads) but never names those siblings, so the differentiation is inferred rather than stated.

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?

The context for use is clear: 'Toll re-reads it about every 10 minutes and POSTs... when its verdict word changes or a new finding appears', plus 'The first read sends nothing', which sets expectations for when nothing will be delivered. It gives no explicit exclusions or routing advice toward alternatives like my_watches (listing existing watches) or unwatch_coin, so an agent must infer those relationships.

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