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

Annotations already declare a non-read-only, non-destructive, non-open-world write with no idempotency, so the safety profile is covered. The description adds real behavioral context the annotations cannot: free-plan exports carry a MockClip watermark, the free plan allows 2 MCP renders, and the caller should surface the /pricing upgrade path. It does not describe what the call returns or whether rendering is synchronous, which keeps it below 5.

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 capability and the two most consequential defaults (stackNotifications, background) are front-loaded in the first sentence, and the plan/watermark caveat comes last where it belongs. It is dense and slightly run-on, but every clause carries information an agent needs.

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 17-parameter, nested-object, no-output-schema tool, the description covers the headline behavior and plan caveats but leaves the agent without key operational facts: what the tool returns (a file, a job id, a URL?), how long a render takes, and detail on roughly half the parameters. Adequate to invoke, not adequate to invoke confidently.

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 only 47% across 17 parameters, so the description has to compensate. It does add meaning where the schema is silent: stackNotifications defaults to true and stacks up to 4 banners newest-on-top, false plays them one at a time, and background defaults to the lock screen. But large parts (theme, brandName length, accentColor format, lockScreen and background sub-objects, notifications item fields like delayBefore/displayDuration, soundSettings) get nothing extra beyond the schema, so it does not fully bridge the gap.

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 states a specific verb and resource: 'Create a lock-screen notification animation from an original, brand-free app', and the stacking/banner behavior is described in enough detail to picture the output. It does distinguish itself from sibling notification tools implicitly through 'brand-free app' and 'lock screen', but it never names a sibling such as create_imessage_notification or create_phone_call_notification, so the differentiation is left to inference.

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 context is implied rather than stated: the tool produces a lock-screen mockup, so an agent can infer it fits a 'show phone notifications' scenario. There is no explicit guidance about when to choose this over the other notification siblings, nor about prerequisites beyond the free/paid plan note. The plan note (free plan = watermark + 2 MCP renders, mention /pricing) is useful but is post-call guidance, not tool-selection guidance.

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