ai_assist

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

Annotations declare readOnlyHint=true and openWorldHint=true, and the description reinforces this with 'does NOT save anything' (no contradiction). It goes well beyond annotations by disclosing the dependency on the Settings → AI model config, the degraded basic-truncation fallback for only three tasks, that other tasks return an error, and that alt_text is unavailable. Rich behavioral disclosure.

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?

Front-loads the most important fact (no saving, write it yourself) ahead of secondary detail. Sentences are dense with em-dashes but every clause carries actionable information; minor run-on structure keeps it from a 5.

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 read-only generation tool with no output schema and no sibling overlap, the description covers the critical gaps: non-persistence, model config dependency, degraded-mode task coverage, and the alt_text exclusion with a routing alternative. Nothing an agent needs to invoke it correctly is missing.

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%, so the baseline is 3 and the schema already documents task/input/site/targetLocale. The description adds value beyond the schema by specifying which task values remain functional without a configured model (meta_title, meta_description, summarize), a constraint that directly affects task selection.

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 ('Run the CMS's writing assistant on a piece of text') and immediately delimits scope by declaring it saves nothing. An agent can distinguish it from sibling write tools like update_content or set_field without opening any 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?

Explicitly routes the agent: 'write the output yourself with set_field/update_content' and 'write it and save with update_asset_alt' for alt text. It also names when NOT to expect this tool to work (alt_text is refused) and names the alternative, which is exactly the when/when-not/alternative pattern.

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