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

With no annotations, the description carries the full burden and does substantial work: it discloses that the call is a purchase that charges credits, that the control token is one-time and must never be shared, that re-purchasing the same window is discouraged, and what the response contains. It does not state funding/payment prerequisites, whether a failed or duplicate purchase is refunded, or what happens if the token is lost, which is the main remaining gap for a paid mutation.

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?

Four short sentences, front-loaded with the action and the return, then the usage condition, the prohibitions, and the response shape. Every sentence carries distinct information with no restatement of the name.

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 two-parameter paid mutation with no annotations and no output schema, the description covers purpose, cost, return fields, and token hygiene. The omissions are the undocumented 'chain' parameter and the lack of any statement about payment source or failure/refund behavior.

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?

Only 'symbol' is documented in the schema (50% coverage), and the description adds no parameter-level meaning at all beyond the phrase 'for one asset'. The 'chain' parameter is undocumented in both the schema and the description, so an agent gets no guidance on whether chain is required, defaults, or which values are accepted.

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: 'Buy a 24h Oracle Watch window for one asset and return the one-time control token.' It immediately distinguishes the tool from the per-snapshot sibling by contrasting 'poll throughout a window' with 'paying per snapshot', so an agent can differentiate it from oracle_watch and oracle_watch_window_control without opening either 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?

It gives an explicit when-to-use condition ('an agent will poll throughout a window instead of paying per snapshot') and an explicit when-not ('Do not use it repeatedly for the same window'). The alternative is described functionally rather than named, so the agent must infer that oracle_watch is the pay-per-snapshot path and that oracle_watch_window_control is the follow-up for an existing window.

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