watch_tokenpull

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

The description discloses that the tool never blocks or loops, that interval_s is advisory and echoed back, and that submit is rate-limited to once per 5 min per platform+window. These details go beyond the annotations (idempotentHint, openWorldHint) and provide important behavioral context.

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 well-structured with the key behavior front-loaded. It is slightly verbose but every sentence adds value. Could be tightened slightly but is effective.

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?

Given the tool has an output schema (not shown but present), the description does not need to detail return values. It adequately covers the main behavior, polling mechanism, submit behavior, and rate limiting. For a tool with 4 parameters, this is complete.

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%, but the description adds meaningful additional semantics: it explains that interval_s is advisory and echoed, that submit defaults to false (preview-only), and that window=7d is most sensitive. This exceeds the baseline of 3.

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 the tool pulls token logs and returns the current cascade for a watched window, with a specific verb ('pulls') and resource. It distinguishes itself by emphasizing one poll per call and non-blocking behavior, which separates it from siblings like 'tokenpull' that may batch or block.

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 explains when to recall the tool at a desired cadence, how interval_s is advisory, and the behavior of the submit parameter. It does not explicitly compare to siblings or state when not to use, but provides clear usage context.

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