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

Goes well beyond the annotations by disclosing that prompt-based generation is async (~1-2 min), applied automatically, and how to poll it. Also surfaces a critical prerequisite and a failure mode (image shows a stranger without referenceImageUrls). Annotations only cover the safety profile, so this extra context is valuable.

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?

Three dense sentences, front-loaded with the core action and split by the two operating modes. Every clause carries actionable information; 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?

With no output schema, the description still covers the async lifecycle, status-check path, and identity prerequisite for a 4-param mutation tool. An agent has everything needed to invoke it correctly.

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 real meaning: imageUrl is an instant swap, prompt triggers async generation, and referenceImageUrls must be paired with prompt and sourced from use_character_reference. This clarifies parameter interactions beyond the schema.

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 and resource ('Replace a post's image entirely'), which cleanly distinguishes it from siblings like add_image_to_post and edit_image. An agent can identify the operation 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?

Explicitly lays out the two modes (imageUrl for instant swap vs prompt for AI generation) and names the prerequisites: call use_character_reference first for named people, and check with get_task_status for async results. Clear when-to-use guidance with named alternatives.

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