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

Beyond the annotations, the description discloses concrete side effects: other Sources and searches are untouched, certain inputs are refused, manually stopped Sources return in blockedSources on resume, and the operation does not consume credits. These are meaningful behavioral details not inferable from annotations alone.

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 dense and front-loaded, with no filler. The only slight weakness is the final sentence, 'Pausing is also how you stop the polling that does,' which is grammatically awkward and less clear than the rest.

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 3-parameter mutating tool with no output schema, this description provides inputs, restrictions, side effects, fallback behavior, and cost impact. An agent has enough context to decide when to call it and what to expect, including the blockedSources nuance on resume.

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 schema already documents id and action and enumerates source values; the description adds value by tying action to real-world state changes and by surfacing validation rules about un-polled Sources and the last polling Source. It does not describe each enum value, but those names are self-explanatory and the schema covers the rest.

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 states a specific verb pair ('pause/resume') and an exact resource ('one Source of a keyword'), then immediately clarifies scope: 'without touching its searches or the other Sources.' This clearly distinguishes it from related tools like keyword_manage and keyword_source_set.

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-not case: refusal on the last still-polling Source, and directs the agent to use keyword_manage instead. It also adds cost guidance ('Free — does not charge credits') and frames pausing as the way to stop polling, helping the agent choose the right operation.

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