image.load

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

Annotations already provide readOnlyHint=false, destructiveHint=true, openWorldHint=false, and idempotentHint=true, so the safety profile is mostly in structured data. The description adds the 'reuse' behavior and the 'bounded color-space policy' nuance, which is useful, but it doesn't clarify the destructive/transactional behavior beyond what annotations imply. No contradiction exists.

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 a single, well-structured sentence that front-loads the primary action and then packs the key constraints efficiently. Every phrase adds meaning—'load or reuse' clarifies idempotency, 'arbitrary absolute local path' sets path expectations, and 'bounded color-space policy' and 'active structural transaction' define the operating context. There is no filler.

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?

The tool has 5 parameters including an idempotency key and an expected generation counter, plus a destructive annotation and an output schema. The description explains the action and the transaction/color-space context, but does not mention the return value, the failure semantics of expected_scene_generation, or how idempotency_key affects call behavior. For an agent to correctly invoke this among many transaction-managed tools, more would be welcome, though the output schema likely covers return shape.

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 schema carries almost no explanatory weight for the parameters. The description mentions 'local path' (path), 'color-space policy' (colorspace), and 'active structural transaction' (transaction_id-related state), which maps to some parameters. However, it does not add meaning for idempotency_key or expected_scene_generation, so with zero schema coverage the description only partially compensates.

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 names a specific verb ('load or reuse'), a resource ('image from an arbitrary absolute local path'), and a key constraint ('bounded color-space policy inside the active structural transaction'). It distinguishes itself from image.inspect and material.texture.bind by covering image acquisition rather than inspection or binding, though it does not explicitly name a sibling.

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 implies the tool is for loading/reusing images from local paths inside a transaction, but it does not explicitly state when to prefer this over image.inspect or material.texture.bind, nor does it mention the idempotency key and transaction prerequisites. The context and transaction language are present, but exclusions and alternatives are left to the agent to infer.

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