get_characters

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

No annotations exist, so the description carries the full burden. It discloses the read-only nature, free cost, the complete status enum semantics, the meaning of rejection, and the financial risk of repeated retries. This is unusually transparent for a status-list tool.

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 long and dense, but each section earns its place: purpose, status definitions, and retry decision logic. It is front-loaded with the core read operation before diving into edge-case handling.

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?

With no output schema, the description serves as the only documentation of return structure and status behavior. It covers key statuses, rejection reasons, retryability, and next-step tools. It stops short of showing a concrete example response, but nothing essential for calling the tool 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?

There is only one parameter and schema coverage is 0%, so the description should compensate. It refers to the resource as '某一集', which maps to episode_id, but it does not explain the parameter by name or add format/usage detail beyond the schema's integer requirement.

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 specific verb ('读') and resource ('某一集的角色列表'), and further specifies the contained fields: names, portrait/sheet readiness. It clearly separates this read-only status tool from generation siblings by framing it as a status inspection endpoint.

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?

Includes explicit actionable guidance: do not re-trigger pending items, retry once for consistency_rejected via generate_character_sheet, and run run_precheck before retrying structurally impossible rejections. This names exact alternatives and the conditions that select them.

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