view_image

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

No annotations are provided, so the description carries the full burden. "Without importing it" usefully discloses that the workspace is not mutated and no asset is created, but the description says nothing about what comes back (image content vs. path), whether viewing a large image costs significant context, or how the max_size cap behaves.

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?

A single front-loaded sentence of roughly twenty words with no filler. The scope first, the qualifier second — nothing wasted.

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 two-parameter read tool this is nearly adequate: purpose and the non-importing constraint are clear. But with no annotations, no output schema, and an undocumented max_size, an agent still cannot predict the return payload or the meaning of the size limit.

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 description must compensate for both parameters and does not. The path parameter is inferable, but max_size (default 1024) is entirely undefined — there is no indication whether it means pixels on the long edge, a byte cap, or a token budget.

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 concrete verb and resource ("Look at an image file in the workspace") and adds the key qualifier "without importing it," which tells an agent this is a read/view operation. It distinguishes itself implicitly from import_image and analyze_image, but never names those siblings explicitly.

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 parenthetical "(reference, generated output, export)" gives concrete situations where this tool applies, and "without importing it" signals the boundary against the import_* family. It stops short of naming alternatives or stating when NOT to use it (e.g., when pixel analysis via read_pixels/analyze_image is needed).

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