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

The destructiveHint annotation already indicates the action is destructive, and the description reinforces this with the word 'delete.' It does not describe irreversibility or cascading effects, but given the annotation covers the core destructive nature, the description is adequate.

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 extremely concise, starting with the essential action and followed by a brief clarification. No unnecessary words or redundant information are present.

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 description and schema provide enough information to invoke the tool, but they do not clarify whether paragraph_id is globally unique or scoped to the sound item, nor do they mention potential effects on paragraph ordering. Given the sibling reorder tools exist, this missing context could be relevant.

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?

Both parameters have schema descriptions that reference the relevant list tools ('cms_list_sounds' and 'cms_list_sound_paragraphs'), providing helpful context. The description's 'context: id, paragraph_id' line adds minimal extra value, but the schema coverage is complete.

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 states the action ('Delete one sound paragraph') and identifies the target resource. It is easily distinguishable from sibling paragraph-deletion tools by the 'sound' qualifier in both name and description.

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 mentions 'by paragraph id' and lists the two parameters, but it does not explain when to use this tool versus deleting an entire sound item or deleting other paragraph types. The context line 'id, paragraph_id' hints at the parameters but adds little guidance.

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