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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: it enumerates what the editor supports (area marking, descriptions, reference photo, product picks/@mentions), states the key limitation that it does not generate/save/publish, specifies returning editorUrl off-app, and adds the guardrail 'Never claim the edit is done'. This is rich behavioral context for a UI-opening, non-mutating 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?

The description leads with the action and its boundary up front, then adds usage, capability, and return notes. It is a bit long but each sentence carries distinct information (capability list, limitation, routing, return channel, guardrail); nothing is redundant.

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 read-only UI-opening tool with no output schema and no nested params, the description covers what happens, what the user can do inside the editor, and the editorUrl return path. The main gap is that it does not fully disambiguate the three input parameters despite their 0% schema coverage.

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 has to carry parameter meaning. It does partly: 'Prefill only the requested instruction' maps to the instruction param, and 'an owned post or a specific carousel image' hints at postId vs mediaItemId. But it never names the parameters or explains required/optional status or the carousel-image relationship in explicit terms.

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 and resource ('Open the existing Edit AI Image modal for an owned post or a specific carousel image') and immediately bounds its scope ('This only opens the editor; it does NOT generate, save or publish an edit'). An agent can distinguish it from siblings like edit_image, add_image_to_post, and change_image without opening any schema.

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?

Gives clear trigger conditions: 'Offer this when precise visual corrections or product references would help; use it when the user accepts or asks to open the editor.' It also rules out generation, which implicitly routes to a different sibling, though it never names that alternative explicitly.

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