edit_image

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

Annotations already carry readOnlyHint=false, idempotentHint=true, and destructiveHint=false. The description adds useful context on top: the operation is billable, the source remains unchanged (non-destructive), and several input modes (masks, URLs, multiple references) are unsupported. No contradiction with annotations exists.

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 with zero filler. The core action and constraints are front-loaded, and each sentence contributes a distinct piece of information: what it creates, what inputs it requires, and what behaviors are excluded.

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 6-parameter tool with no output schema, the description covers invocation requirements well but does not state what is returned on success, how the billable image is surfaced, or whether the result is an artifact id. The sibling get_operation hints at async operation tracking, but this is never connected. Some return-semantics gap remains.

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 only 17%, so the description must compensate. It clarifies the oneOf disjunction between source_artifact_id and source_path, qualifies source_path as 'approved absolute PNG', and explains operation_id as a fresh UUID and prompt as 'self-contained'. Optional size/quality enums are not described, but they have single allowed values and defaults, so the gap is minor.

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 opening clause 'Create one new billable image from exactly one explicit source_artifact_id or approved absolute PNG source_path' names the verb, resource, and the key input constraint. It clearly implies editing an existing artifact rather than generating from scratch, distinguishing it from the generate_image sibling without confusion.

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 gives strong input conditions ('exactly one', 'approved', 'self-contained') and explicitly lists what is unsupported ('masks, URLs and multiple references'). However, it never explicitly says when to prefer this over generate_image or get_operation; the boundary is implied by the word 'source' rather than stated.

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