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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses server-side processing, that the LLM key never leaves the vault, the metered billing as a tollbooth fare, and refund conditions (no LLM key or empty upstream response). It also clearly states that the tool returns suggestions rather than applying edits directly, which is essential behavioral context.

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 concise and front-loaded with the core purpose. It uses three short paragraphs: what it does, how to use it, and billing/refund policy. Every sentence contributes useful information with no filler. It could be slightly tighter, but it is appropriately sized for a paid, multi-parameter tool.

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?

Given the tool's complexity (paid, 7 parameters, output schema), the description covers the key aspects: input semantics, return value with exact structure, and billing implications. It leaves some gaps, such as the purpose of dpop_token and explicit error handling, but the output schema and sibling context fill some of these. Overall it is complete enough for an agent to invoke the tool correctly.

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 86%, with most parameters described in the schema. The description adds cohesion by explaining how region, full_text, instruction, voice, and bans fit together in the workflow. It also clarifies the bans format and the billing role of npub. While the schema already provides parameter-level details, the description adds cross-parameter context that helps the agent construct a correct request.

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 opens with a clear verb-object: 'Refine a flagged region of a post with an LLM.' It specifies the exact scope (flagged region) and method (LLM, server-side), distinguishing it from siblings like update_post or create_post. It also states the return format, reinforcing the tool's purpose as a suggestion generator rather than a direct editor.

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 clearly implies when to use this tool: when a post region is flagged and needs LLM-based refinement. It explains what inputs to send and what to expect in return. However, it does not explicitly mention alternatives or exclusions, such as 'for full post edits use update_post' or 'when no LLM key is configured, use something else.' The context is clear but not exhaustive.

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