plan_screenshot_changes

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

Annotations already provide readOnlyHint=false, openWorldHint=true, and destructiveHint=false, but the description adds key behavioral nuance: merge does not remove verified images, replace does, pending/unknown bytes block merge, and writes only happen through an approved apply_plan. This is valuable vector beyond the annotation hints.

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 highly dense and front-loaded, with each sentence compact: purpose, merge/replace behavior, precondition, application workflow. However, the phrasing uses jargon without definition (e.g., 'capacity gap', 'decoded original bytes', 'final states'), which forces the agent to infer too much from too few words, even if each word is intended to earn its place.

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 tool with no output schema and fairly subtle behavior differences, the description leaves gaps: how to handle pending/unknown bytes, what a plan contains, what 'final state' looks like, and how to report or review the plan. The overall purpose is clearer than many tools, but the complexity of the merged/replaced object is substantial enough that the description should provide more context.

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?

With 0% schema description coverage, the description is expected to explain parameters such as root, locales, version, and platform. The description vaguely suggests 'locales' from the name and 'decoded original bytes' may map to root, but it doesn't clarify what root points to, how version is used, or which locale syntax is expected. This leaves the agent guessing.

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 states that the tool 'plans exact macOS locale change sets from decoded original bytes,' giving a specific verb and resource, and the sibling list clearly separates it from provisioning, metadata, commerce, and signing plan tools. It stops short of a fully plain-language statement of what screenshot lucid sets are or why 'decoded bytes' matter.

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 concrete guidance on when to prefer merge (preserves verified unpaid images) versus replace (explicitly shows removals and missing) and sets a precondition (pending bytes require recovery before merge). It doesn't explicitly name an alternative sibling tool, but no other sibling handles screenshot locale plans, so the implicit guidance is sufficient.

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