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

Annotations only declare the generic mutation profile (readOnly=false, destructive=false, idempotent=false, openWorld=false); the description adds genuinely non-structured behavior: free-plan MockClip watermark, a 2-render free quota, and an instruction to surface the /pricing upgrade path to free-plan callers. That is meaningful operational context the annotations cannot carry. It still omits whether the render is synchronous/asynchronous and what is actually returned, so it is not a 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?

Extremely dense: a single 90+ word first sentence with nested parentheticals, followed by three more long compound sentences. The most actionable instruction for the agent (the free-plan upgrade mention) is buried in the final sentence rather than front-loaded, and the enumeration of chat chrome details could be trimmed. It is information-rich but poorly structured for scanning.

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 22-parameter tool with nested objects and no output schema, the description covers the creative behavior and plan constraints well, but it never explains how the result is delivered (asset URL, job id, async polling) — a real gap when no output schema exists — and leaves roughly two-thirds of parameters undocumented. Adequate but with clear omissions.

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?

With only 36% schema description coverage across 22 parameters, the description must compensate, and it does explain several undocumented ones: flow screen steps and transitions, showTaps, firstDateLine/dateLabel rendering rules, showHeader, myName/myAvatarUrl, and the threads/thread screen objects. But it says nothing about intro, theme, soundSettings, contactName/contactStatus, delayBefore, typingSpeed/typingDuration, or reactions structure, leaving large holes. It adds value but does not close the coverage 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?

Opens with a concrete verb+resource ('Create a Slack conversation animation') and immediately enumerates the visual artifacts produced (headers, avatars, date separators, reactions, typing line). The Slack-specific resource is clear enough to separate it from most siblings, but the description never explicitly names or contrasts an alternative (e.g. create_discord_conversation) even though 21 sibling conversation tools exist.

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 conditional guidance for optional features ('Optionally walk through the app's screens... pass flow', 'without them the clip shows the conversation only'), which implies when to enable flow. However there is no when-to-use-this-tool vs. a sibling, no prerequisites, and no statement of what inputs are mandatory beyond what the schema enforces.

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