Sheet: Attach Image

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

Annotations only carry destructiveHint=false, so the description adds real value by enumerating the refusal conditions and stressing that all refusals happen 'before anything is written' — a meaningful atomicity guarantee. It also hints the payload reports both pixel size and placed size.

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?

Front-loaded with the core action in the first sentence, then scale semantics, then a compact refusal list. The refusal list is slightly telegraphic fragments ('a file that does not exist, a file no image reader can open (named)'), but it is efficient and information-dense.

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 present, the description need not explain returns; it covers the action, scaling semantics, and failure modes. The main omission is the absence of any routing guidance relative to sibling attach/insert tools.

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 100%, so the baseline is 3. The description restates the `scale` semantics (drawing units per pixel, placed size = pixel size × scale) already present in the schema, adding only marginal extra meaning for x/y/rotation.

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 ('Attach a raster underlay') with the key scoping behavior ('at the file's own aspect ratio') and notes it works in both engines. It is clearly distinct from sibling insert-like tools (block_insert, xref_attach) by virtue of the raster resource, though it does not name any sibling 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?

Usage is implied by the refusal conditions (file must exist, must be readable, scale must be positive/finite), which tells the agent what preconditions to satisfy, but there is no explicit when-to-use vs. alternatives guidance (e.g. vs. xref_attach or hatch_add_boundary).

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