image_edit

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: v1 pixel path is a free mean-RGB match only, 'intent' is required metadata that does not select pixel operations, paid generation always fails, and dry-run returns a plan without mutating pixels. It stops short of permissions/auth needs and rate or cost behavior, but the mutation and failure semantics are genuinely informative.

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 Args block is well-structured, but the prose preamble is dense jargon and mildly redundant (the metadata-only nature of 'intent' is stated twice), and the critical scoping fact is buried behind a confusing first clause. It is serviceable but not cleanly front-loaded.

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?

Because an output schema exists, return values need not be explained, and the description covers behavior, all parameters, dry-run, and the paid-generation limitation. The main remaining gap is sibling differentiation from still_match/still_grade, which an agent needs for correct tool selection.

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 0%, so the description must compensate, and the Args block documents all seven parameters with added meaning: 'intent' is audit text and not a NL pixel director, 'prefer' accepts 'edit'/'gen', 'allow_paid_gen' is explicit paid permission defaulting False, and 'dry_run' means plan-only. This adds real semantics beyond bare parameter names.

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 'Establish-locked still match with plan/receipt' is a jargon-heavy noun phrase rather than a clear verb+resource, though the body does clarify it performs a free mean-RGB match of a source still against a reference. It never distinguishes itself from siblings like still_match, still_grade, or still_package, so an agent cannot route confidently.

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?

Usage is only implied: the description notes that paid generation requests fail (no adapter), that 'prefer' defaults to 'edit', and that dry_run plans without mutating. It gives no explicit when-to-use/when-not guidance or named alternative tools, leaving the agent to infer context.

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