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

Discloses far more than the annotations: exact credit cost per length tier, background/async execution, that output is not published, the Autopilot-equivalent content properties (real sources, only existing links, CTA, Article+FAQ schema), and idempotency_key retry behavior. Annotations only cover readOnly=false and openWorld=true, so this description carries the behavioral burden well.

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?

What the tool does is front-loaded in the first sentence; credits, async execution, the publish handoff, and idempotency each get exactly one purposeful clause with no filler or repetition.

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 7-parameter, credit-spending, async generation tool with an output schema, the description covers cost, execution model, non-publication, downstream step, and retry safety. Return-value details are correctly left to the output schema.

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 57%, and the description compensates for the gaps that matter: it maps each length enum value to its credit cost (1/2/3/4) and explains idempotency_key semantics ('Retries with the same idempotency_key never spend twice'). It says nothing about tone, language, or integration_id, leaving some parameters to the schema alone.

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 ('Write a new AI article for a keyword') and immediately positions it against siblings: generation is distinct from publish_article ('The article is generated in the background and is NOT published'). An agent can separate this from publish_article, replace_article, and get_article without opening a 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?

Gives a concrete precondition ('check get_plan_and_credits first') and an explicit next-step alternative ('call publish_article for that'). It does not, however, address the modify-existing path (replace_article) or other when-not conditions, so it falls just short of fully explicit routing.

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