delete_post

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

With no annotations provided, the description carries the full behavioral burden, and 'Preview by default' is a genuinely valuable disclosure: it tells the agent that a default call is non-destructive and that actual deletion requires opting into execution. This is safety-critical context for a delete tool and goes beyond what the schema's default value alone conveys. It does not, however, mention irreversibility, cascading deletion of comments/reactions, or any special permissions needed.

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 short sentences totaling nine words, with the core purpose front-loaded and the critical behavioral caveat placed immediately after. Every word earns its place; there is zero redundancy or 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?

For a destructive tool with no annotations and 0% schema coverage, the description discloses the single most important trait (preview by default) and the output schema covers return values, so the agent is not entirely in the dark. But it omits the natural usage workflow (preview, then confirm with execute=true), the destructive consequences of execution, and any mention of auth or permissions. It is minimally adequate but leaves meaningful gaps for a delete operation.

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 0%, so the description must compensate, and it partially does: 'by URN' clarifies that post_urn is the post identifier format, and 'Preview by default' explains the execute parameter's default behavior. However, it never explicitly states that setting execute=true is what triggers the actual deletion, leaving the key param semantics implicit. For a two-parameter tool, partial coverage of both params is adequate but not thorough.

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 states a specific verb and resource ('Delete a post by URN'), making the core purpose unmistakable even without opening the schema. It does not explicitly distinguish itself from sibling tools like create_post or delete_reaction, but no sibling competes for the same verb+resource pair. The 'Preview by default' clause introduces mild complexity about what a default invocation actually does, which slightly tempers clarity.

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 gives no guidance on when to use delete_post versus alternatives, and no exclusions or prerequisites (e.g., post ownership, auth requirements) are stated. 'Preview by default' hints at a preview-then-execute workflow but never tells the agent to run once with execute=false before confirming with execute=true. An agent must infer the invocation pattern on its own.

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