hdr_compress

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

Annotations already declare destructiveHint=true, and the description's 'Checkpoints first' instruction aligns with and reinforces that destructive behavior, adding practical advice. It also clarifies the intended image state (non-linear) and the target (bright cores), which goes beyond the annotation. No contradiction; the description adds extra behavioral context without conflicting with structured 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 two concise sentences with no fluff. The purpose is stated first, followed by a critical prerequisite ('Checkpoints first'). Every word earns its place, and the structure front-loads the core function.

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 5 parameters, nested objects, and no output schema, this description is too brief. It provides purpose and a precondition but omits essential details: how the image is modified, what the parameters do, return behavior, and when it is appropriate relative to other processing steps. The annotations cover destructiveness but not operational completeness. Given the tool's complexity, key information is missing.

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 40% (only 'params' and 'checkpoint' have descriptions). The description does not explain any parameters—neither id, layers, iterations, nor the semantics of the params object. Since coverage is low (<50%), the description should compensate, but it is silent on parameters, leaving the agent to infer from names alone. This is a clear gap.

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 clearly states the tool applies HDRMultiscaleTransform to recover bright cores (galaxy cores, nebula centres) on non-linear images. It names a specific verb, algorithm, and target, making the purpose unambiguous. It does not explicitly differentiate from siblings, but the specialized nature (HDRMultiscaleTransform for bright cores) is distinct enough among the many processing tools.

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 provides a usage context: it is meant for non-linear images and advises 'Checkpoints first,' implying a pre-execution safety step. However, it does not explicitly state when to use this tool versus alternatives (e.g., other HDR or stretching tools) or when not to use it. The guidance is present but shallow, lacking exclusions or comparisons.

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