goodnotes_crop_image

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds real substance: the source may be replaced with cropped pixels, original pixels are retained privately, and the result is verified after reload. That tells the agent the source document is mutated but recoverable, which is exactly the context the annotations alone cannot convey. It stops short of covering failure modes or whether re-invocation with the same operationId is safe.

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?

Three short sentences with no filler, and the core action is front-loaded. The phrasing is dense and slightly jargon-heavy ("prepared rectangle," "privately"), but each sentence adds a distinct fact: the operation, the source mutation, and the backup plus verification.

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 destructive mutation with a nested object, zero schema descriptions, and no output schema, the description covers the mutation risk and post-write verification reasonably well. It remains incomplete on provenance of cropId, the idempotency meaning of operationId, and what the agent should do if verification fails.

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 carry parameter meaning, and it only partly does: "fractions of the current source preview" clarifies that region x/y/width/height are normalized, which is genuinely useful given the nested object. However, cropId (evidently a handle prepared elsewhere) and operationId (presumably an idempotency key given its pattern) are never explained, leaving two of three required parameters opaque.

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 says to "Apply a prepared rectangle in fractions of the current source preview" and later mentions "cropped pixels," so the crop-ish nature is inferable, but the verb "apply" and the noun "source preview" are jargon rather than a specific verb+resource statement. It never explicitly says it crops the current image, nor does it distinguish itself from goodnotes_image_crop_info, which the phrase "prepared rectangle" clearly gestures at.

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?

"Prepared rectangle" implies the crop region must be obtained beforehand, but no tool is named and no prerequisite, precondition, or alternative is stated. An agent gets no explicit when-to-use guidance and must guess that goodnotes_image_crop_info is the companion that prepares the rectangle.

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