Channeling

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

Annotations already declare it is not read-only, not idempotent, open-world, and non-destructive, but the description adds value beyond them: it discloses the exact output artifacts, that results are written to disk and their paths returned (important with no output schema), and that the call is credit-priced ('Free for a limited time; priced by the server'). It stops short of describing failure modes, overwrite behavior, or rate/credit-consumption specifics.

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 purpose is front-loaded and the sentences are short and largely non-redundant. The pricing sentence is the weakest link but still earns its place for a credit-consuming call, and the description stays compact despite the tool's complexity.

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 no output schema, the description correctly carries the return-value burden by naming the PSD bundle, preview PNG, and returned file paths, and it flags the paid-call aspect. Given the 100% schema coverage of 14 parameters and existing annotations, the remaining omission (async/task_id flow, credit-estimate behavior) is minor and largely covered by 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 description coverage is 100%, so every one of the 14 parameters is already documented in the input schema, and the description adds essentially no parameter-level meaning (no mention of trap_mode, n_clusters, review_settings, or wait). The baseline of 3 applies when the schema does the heavy lifting.

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 gives a specific verb and resource: 'separate the design into print screens (spot channels)', and it names the concrete artifacts produced (multichannel PSD, preview PNG). It is clear about the operation, but it never contrasts itself with plausible siblings such as td_colour_layering, td_colourways, or td_foil_separation, so the agent gets no explicit differentiation.

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?

'Best for: preparing a design for screen or rotary printing' supplies a usage context, so the intended situation is implied rather than absent. However, there are no when-not conditions and no named alternatives among the many separation/layering siblings, leaving routing decisions to inference.

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