crop

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

With no annotations, the description carries the full load; it does disclose two meaningful behaviors: the operation re-encodes (so it is a write, with quality/cost implications) and invalid rectangles fail fast instead of being clamped. It does not say whether the source file is preserved, where the result lands, or whether re-encode alters quality settings, leaving gaps for a mutation tool.

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?

Two short sentences, front-loaded with the action and its parameterization, then the one failure mode that matters. 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?

For a 7-parameter write tool with no annotations and no output schema, the description covers the core operation and one error case but is silent on the return value (e.g., resulting file path) and on non-destructive behavior toward the input. Adequate, not complete.

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 100%, so the schema already explains every parameter including output path and overwrite semantics. The description's restatement of (x, y, width, height) as a pixel rectangle adds essentially nothing beyond the schema; baseline 3 applies.

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?

Specific verb ("Crop") plus resource ("a video") and an explicit geometric model (x, y, width, height) with the extra detail that the result is re-encoded. It is clearly distinguishable from transform siblings like scale or reframe, though it never names those siblings to reinforce the boundary.

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 rather than stated: you crop when you want a sub-rectangle of the frame. The second sentence gives a validity constraint (out-of-bounds rectangles are rejected) but no guidance on when to pick this over reframe, scale, redact_region, or clip, nor any stated prerequisites.

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