Edit an image

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

Annotations are minimal (all hints false), so the description carries the full behavioral burden. It discloses rich, non-obvious behavior: untouched composition/aspect ratio/people/text are preserved, the saved brand's real name/website are pinned to prevent invented branding, the real logo is attached when requested, and removal:true prevents re-adding brand elements. It also notes credit cost and return value (new image URL). This goes far beyond the structured fields.

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?

The description is longer than average, but every sentence earns its place: examples, parameter guidance, behavioral nuances, and alternatives are all actionable. It is front-loaded with purpose and ends with routing to siblings. Slightly dense, but 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 4-parameter tool with no output schema, this description is complete: it covers all input formats, required parameters, optional mask and removal flags, behavioral guarantees, credit cost, return value, and alternative tools. An agent has everything needed to invoke it correctly without external knowledge.

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 description coverage is 100%, so baseline is 3. The description adds meaningful extra semantics: it explains instruction as plain-language with examples and says to pass the user's own words for removal; it clarifies image source types; it elaborates removal behavior beyond the schema's boolean; and it cross-references generate_image for mask usage. This raises it above baseline.

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?

The description opens with a specific verb and resource: 'EDIT an existing image in place with a plain-language instruction and keep everything else.' It gives concrete examples ('make the headline bigger', 'remove the person on the left') and explicitly differentiates from siblings: 'For a new image from a prompt use generate_image; to rebuild a competitor's ad for your brand use clone_static.' An agent can immediately tell this tool edits, rather than generates or clones, images.

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?

The description states exactly when to use this tool versus alternatives, naming generate_image and clone_static by name. It also prescribes when to set removal:true (when stripping text, branding, or objects) and when to pass mask (for a precise region). This gives the agent clear decision criteria, not just a vague purpose.

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