Resize image

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

Beyond the annotations, the description discloses the 16384 px per-side cap, the output naming convention <name>-<W>x<H>.<ext>, the format default behavior, and the ordering fact that a crop is applied before resizing and overrides ratio. The only tension is that it describes writing output files while annotations claim readOnlyHint=true; this reads as a pure-transform-plus-new-file pattern rather than a true contradiction, but it is worth noting.

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 core verb and aspect-ratio rule lead, followed by progressively optional features (fit, crop, presets, format, size cap, naming), which is a sensible information hierarchy. The middle fit/crop clause is dense and slightly run-on, costing a bit of scannability.

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 12-parameter tool with a nested crop object and no output schema, the description covers behavior, limits, and the naming of the written file, which is what an agent needs to call it. It stops short of saying what the tool returns (path vs. metadata) and whether the result is ever returned inline except via returnBase64.

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 all twelve parameters are already self-documented; the description mainly restates them. It does add relational meaning the schema lacks — width/height interdependence, crop-before-resize precedence, and fit's 'nothing is stretched' rationale — but presets are only listed, not mapped to sizes, and output/returnBase64 semantics are left to the schema.

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 opening sentence is a specific verb+resource statement ('Resize an image by pixels or percent, keeping the aspect ratio') and the rest enumerates the exact levers (fit modes, crop ratio/box, presets, formats). It does not name sibling tools, so an agent must infer on its own why image_resize rather than image_crop or image_convert.

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 of the parameters is well explained ('Give width or height (the other side follows), or both'), and the fit modes are given concrete semantics. However, there is no when-to-use/when-not guidance relative to the sibling image tools (image_crop, image_convert, image_compress), and no stated prerequisites about input image accessibility.

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