delete_asset

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

Annotations confirm destructive and non-idempotent behavior, but the description adds substantial context beyond them: both the database row and the stored binary file are removed, references are not blocked, and pages silently lose the image via null resolution. It also discloses the return shape ({ok:true}). This is genuinely useful behavioral disclosure.

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?

Four tight sentences, front-loaded with the irreversible action, then the consequence, then the mitigation, then the return value. No filler.

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?

Though there is no output schema, the description supplies the return value, the destructive scope, and the side effects on dependent content. Nothing an agent needs to call this safely is missing.

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 description coverage is 100%, so documentId and site are already fully documented in the schema, including the pointer to list_sites and list_assets. The description adds no parameter-level detail, so the baseline 3 applies.

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?

States a specific verb and resource — 'Permanently delete a media asset' — and immediately clarifies scope: 'the database row and the stored file.' The word 'permanently' distinguishes it from the softer sibling trash_content, so an agent can tell the two apart without opening either schema.

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?

Provides a clear prerequisite: content pointing at the asset must be cleared or replaced first, because delivery resolves dangling references to null. It gives the condition for safe use but never names the obvious alternative (trash_content) for non-permanent removal, so it stops short of explicit alternatives.

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