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

The description goes well beyond the annotations by detailing the exact data categories returned (identifiers, required inputs, credit behavior, Space output behavior, browser-only setup boundaries) and explicitly stating no generator is run. Since annotations already mark readOnlyHint and destructiveHint, this richer context provides the agent a full behavioral picture.

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?

Two sentences, both purposeful and front-loaded. The first sentence gives the usage trigger, and the second lists the key outputs and the read-only nature; no filler or repetition of schema/annotations.

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?

No output schema exists, so the description compensates by listing the exact content categories an agent can expect. With zero params, no side effects, and read-only annotations, there are no other operational boundaries that need explanation for safe and correct invocation.

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?

There are zero parameters, so the description cannot add per-parameter meaning; the baseline for 0 params is 4. The description still usefully summarizes what kind of information the tool returns, which is the closest possible semantic content for a parameterless list operation.

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?

Description states a clear verb ('lists') and resource (available DocuWriter.ai generators) while explicitly saying it returns generator identifiers, required inputs, credit behavior, Space output behavior, and browser-only setup boundaries. This distinguishes it from the many generate-* siblings by adding 'without running a generator' and from list-generations by focusing on available generator definitions.

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 a specific when-to-use trigger: when the user asks which generators are available or what inputs a generator requires. It also communicates a when-not boundary through 'without running a generator' and 'Read-only', but it does not explicitly name alternative sibling tools as the get_calls calibration example does.

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