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

With no annotations, the description carries the full burden and does well: it discloses the credit model (poll is zero extra credits after purchase), the one-time token constraint, and that close destroys the window's usability for future polls. It does not cover failure behavior (e.g. polling a token after close, expired tokens) or latency, which keeps it below 5.

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 verb+resource and followed by cost, precondition, and exclusions. Slightly redundant: the return values are stated twice ("Poll returns a fresh signal... close returns the complete window summary and the final signal" then "Returns the signal (poll) or the combined summary (close)").

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?

There is no output schema, so the description must describe returns, and it does for both operations. With no annotations it also supplies the safety/lifecycle context (one-time token, no reuse, zero-credit polling). Only error and expiry behavior is left unstated for what is a token-gated two-mode tool.

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 67% and the schema itself explains only op and window_token. The description adds real meaning beyond that: the token is one-time, poll costs no extra credits while close finalizes the window, and window_id is implicitly the purchased window identifier. The op enum semantics are largely restated rather than extended.

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 pair of verbs (poll/close) against a named resource (an already purchased Oracle Watch window) plus the credential used (one-time oww_ token). It is clearly distinguishable from oracle_watch_window_begin (purchase) and oracle_watch (one-off snapshot).

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?

Explicitly names the required precondition ("only with a window token from oracle_watch_window_begin"), names the sibling to avoid and why ("Do not use it for a one-off snapshot (oracle_watch)"), and adds a lifecycle rule ("never reuse a token after close"). When, when-not, and alternatives are all covered.

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