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

Annotations declare this is a non-read-only, non-destructive, non-idempotent call; the description adds the important cost context that it consumes 'One LLM call against the user's builder budget,' which a caller cannot infer from the annotations. It does not discuss latency, retries, or what happens on repeated calls, so it stops short of a 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 tight sentences, front-loaded with the step identity and the core input/output, then sequencing, then the alternate path. No filler and nothing repeated from the schema.

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 10-parameter, no-output-schema tool it covers the flow, cost, and routing well; return value is only gestured at ('title options back'), and parameters like temperature, useExternalLinks, and useYouTubeVideos rely entirely on the schema. Adequate, though the output shape could be a phrase richer.

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?

With 80% schema coverage the baseline is 3, but the description adds real meaning: it defines what `prompt` should contain (topic, audience, angle) and demonstrates the `articleType` 'remix' case paired with `urls`. This goes beyond the schema strings for the two most decision-relevant parameters.

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 verb+resource ('get title options back') within a named flow ('Article Builder, step 1'), and distinguishes the tool from siblings by naming generate_outline as the next step and remix_from_urls as the batch alternative. An agent can place it precisely in the builder pipeline without opening the schema.

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?

Explicit about when to call it (start of the builder, given a prompt), what to do next (pick a title and call generate_outline with the same prompt/options), and the alternates for a different case (articleType 'remix' with url, or remix_from_urls for all steps). Both the sequencing and the branching condition are stated, not implied.

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