Audit the media library

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

Annotations already declare readOnlyHint=true and destructiveHint=false, covering the safety profile. The description adds the specific checks performed (alt text and unused media) and the reasoning behind them, which is useful behavioral context. However, it does not mention any operational behavior like pagination, limits, or output format, so it adds only modest value beyond annotations.

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 two sentences: the first states the exact scope, and the second offers a concise rationale. No wasted words, and the core functionality is front-loaded.

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 audit tool with three optional parameters and no output schema, the description is reasonably complete. It explains what the tool checks and why it matters. While it does not describe the return format, the agent can infer it from the audit purpose and the well-documented parameters. Slightly more detail on output would make it perfect, but it is adequate.

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 100% and each parameter already has a descriptive comment (limit range, site_id selection logic, check_unused slow behavior). The tool description reinforces the purpose of check_unused by mentioning unused media, but it adds little beyond what the schema provides. Baseline 3 is appropriate given the high schema coverage.

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 uses a specific verb ('Audit') and resource ('media library'), and clearly lists the two distinct checks: images missing alt text and attachments not referenced by content. This distinguishes it from siblings like list_media (which only lists) and audit_content (which audits content, not media).

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 strong contextual rationale for when the tool is valuable (accessibility and disk usage) and implicitly distinguishes it from listing or content audits. It does not explicitly name alternatives or say 'use this instead of X', but the purpose is clear enough for an agent to select it appropriately.

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