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

Annotations already declare destructiveHint, idempotentHint and openWorldHint, so the safety profile is structured. The description adds real context beyond that: irreversibility ('cannot be undone'), the exact set of supported channels, and the not_supported error for unsupported ones. Return shape is not described, but no output schema exists.

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?

Front-loaded with what gets deleted and where, followed by identification and the safety caveat. Dense but every clause carries information; the long parenthetical channel list is the only mild drag.

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 destructive four-parameter mutation tool it covers the essentials: eligible resources, accepted identifiers, error behavior for unsupported channels, and irreversibility. What is missing is how to resolve ambiguity between account_id and channel, and any hint about the response.

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%, so the baseline is 3. The description earns more by explaining post_id accepts either the id returned by posts_publish or a link, and by enumerating the accepted link formats (x.com, youtube.com/youtu.be, numeric facebook.com) – detail the schema does not carry.

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?

Specific verb (delete) plus resource (a post this account published) plus enumerated channels (X, YouTube video, Facebook Page post). Clearly distinguished from sibling publishing tools like posts_publish and from channel-specific deletes such as youtube_delete_video.

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?

Gives an explicit guardrail: delete only when the user explicitly asks for this post. Also scopes which posts are eligible and states that other channels answer not_supported. It does not name sibling alternatives (e.g. youtube_delete_video), which keeps it short of a 5.

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