media

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

The description adds behavioral context beyond annotations (readOnlyHint=false, openWorldHint=true) by explaining that 'download' writes to local storage, that 'prompt' is ignored, and that 'analyze' returns an error. It does not contradict annotations and provides useful safety information.

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 well-organized with sections for actions, parameters, workflow, and legacy info. It is informative and includes examples, though slightly verbose. It earns high marks for clarity but could be trimmed slightly.

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?

Given the tool's medium complexity (7 params, multiple actions, output schema present, sibling tools), the description covers core usage, workflow, deprecations, and even points to the 'help' tool for full docs. It also references external integration (imagine-mcp), making it self-contained and practical.

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 0% schema description coverage, the description compensates by explaining the purpose and required contexts for most parameters (url, media_urls, media_type, output_dir, prompt). However, it omits 'max_items', which appears in the schema but is not mentioned, leaving a 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 clearly identifies the tool as for discovering and downloading media files (images, videos, audio). It distinguishes between 'list' and 'download' actions with specific examples, and notes that 'analyze' was removed. This differentiates internal actions and sets clear expectations.

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?

The description provides a typical workflow ('list then download') and notes that the legacy 'analyze' action is removed, guiding the agent away from invalid calls. However, it does not explicitly compare with sibling tools like 'extract' or 'search' to indicate when to use this tool instead.

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