watch_tokenpull

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

Beyond the annotations (idempotentHint: true, openWorldHint: false), the description discloses important behaviors: calls never block or loop, interval_s is advisory, and the submit path is rate-limited to once per 5 minutes per platform+window and requires enrollment. This adds substantial context that is not present in the structured annotations.

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?

The description is two sentences, front-loaded with the key behavioral point ('One poll per call'), and every clause carries useful information. There is no redundancy or filler; it is concise yet comprehensive.

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 tool with multiple optional parameters, an output schema, and an optional submit path, the description fully covers the operational model, rate limits, prerequisites, defaults, and the non-blocking nature. No significant gaps remain for an agent to select and invoke the tool 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?

The input schema already has 100% description coverage, but the tool description enriches it further: submit requires enroll and is rate-limited, interval_s is advisory and echoed back as poll_interval_s, and the default behavior is preview-only. This goes well beyond the schema descriptions, making the parameters' practical semantics clear.

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 clearly states what the tool does: 'One poll per call: pulls your local token logs and returns the current cascade for the watched window.' It uses a specific verb (pulls) and resource (local token logs), and distinguishes itself from sibling tools by emphasizing it never blocks or loops and by explaining preview-only vs submit modes.

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 description gives explicit usage guidance: 'Re-call at your desired cadence to watch for changes' and notes that interval_s is advisory only and echoed back as poll_interval_s. It also explains when to use submit:true (with an enrolled device) and when to stick with preview-only (default), effectively covering when and when-not to use the tool.

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