assist_writing

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

Annotations declare readOnlyHint=true/openWorldHint=true, and the description is consistent ('It saves nothing'). Beyond that it adds substantial context the annotations cannot: the {result, provider} return shape, the truncation fallback when no model is configured, which tasks are refused and why, and the permission requirements. No contradiction with readOnlyHint since nothing is persisted.

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?

Dense but front-loaded: capability list first, then the critical 'saves nothing' contract, then fallbacks, then the alt-text exception, then permissions. Every sentence carries actionable information with no filler.

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 multi-task generation tool with no output schema and open-world behavior, the description covers return values, persistence contract, model dependency, refusals, alternative tools, and access control. 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, but the description adds meaning beyond the schema: it clarifies that 'variants' yields a JSON array of exactly 3 strings, that write expects a topic/brief, and that alt_text is refused. These operational details about parameter behavior are not fully derivable from the enum listing 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 concrete verb+resource ('Run the CMS's writing assistant on a piece of text') and then enumerates the actual task space (SEO text, summaries, polishing, rewrites, variants, translation, drafting, schema.org fields). This clearly separates it from sibling content tools like set_field or update_content, which persist rather than generate.

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: 'It saves nothing — write the result with set_field or update_content' and 'write that yourself and save it with update_asset_alt'. It also states the precondition for the model dependency and the permission/role scope (Author limited to their own sections), plus which tasks are refused.

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