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

Beyond the read-only hints in annotations, the description specifies vital behavioral traits such as the returned data format (metadata only), the sorting criteria (newest first), and its primary limitations (does NOT display images). This prevents common AI misuse.

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 is perfectly balanced, front-loading the primary function and immediate limitations, and efficiently using comparison and instruction to guide the user through alternative tool selections.

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?

The definition is exceptionally complete; it clarifies the scope, the content of the return value (metadata vs. images), its sorting mechanism, and its proper interaction pattern with other tools, leaving no ambiguity for the AI agent.

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?

While schema coverage is 100%, the description adds semantic value by listing exactly which metadata fields are returned (id, truncated prompt, model, created date), which is necessary context for the agent to understand the value of the 'count' parameter.

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 is highly specific, stating it returns 'asset METADATA only (id, truncated prompt, model, created date)' and establishes 'newest first' as the sorting behavior. It clearly defines what the tool output contains, which is critical for an asset library.

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?

It provides explicit guidance on usage: it explicitly forbids using the tool to show pictures and routes users to the 'show_media' sibling instead. It further narrows the intended use case to 'when you need ids/metadata for another tool or a plain text list.'

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