Selection

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

Annotations declare readOnlyHint=false, idempotentHint=true and openWorldHint=false, so safety/idempotency are already covered. The description adds genuinely new behavioral context: a selection is state that scopes draw, transform and recolor, which explains the side effects of this tool on other tools. It doesn't say what happens to a prior selection under each op, but with annotations present this is solid added value.

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 tight sentences: purpose first, op inventory second, rationale third. Zero filler; every clause carries information an agent needs.

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 an output schema, annotations and a richly described 10-parameter schema, the description covers the conceptual surface well. Its only notable gap is that it never links ops to their required parameters (e.g., rect needs 'rect', color needs 'color'/tolerance/contiguous), which the agent must infer from the schema.

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 80%, so most parameters (mode, frame, layer, amount, sprite, tolerance, contiguous) are already documented — baseline 3. The description goes beyond by explaining the meaning of each op value, including that 'color' selects every pixel matching a colour, which the enum alone does not convey.

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+resource ('Read or change the active selection') and then enumerates all nine ops with brief semantics for the non-obvious ones ('color' = every pixel matching a colour). An agent can distinguish this from draw, transform, recolor and read_pixels without opening any 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?

Provides a clear rationale for using selections: 'A selection scopes draw, transform and recolor, which is usually cheaper and safer than masking by hand.' That tells the agent when a selection is the right mechanism, but it gives no explicit exclusions or routing between ops (e.g., get vs read_pixels) and no prerequisites.

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