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

Annotations indicate write-safe behavior but not specifics. The description adds meaningful behavior: defaults for Image 1/Image 2, override paths, the style_id exclusion, and credit-cost relationship to create. It does not state the exact mutation extent or what happens to the existing story, but the annotations plus the add-panel principle cover the core safety profile. This is solidly transparent without being verbose.

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?

Four short sentences carry a dense but efficient payload: purpose, one caution, defaults, and override workflow. Nothing is redundant or bloated. The main directive is front-loaded and the operational detail follows logically.

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?

This is a complex tool with 11 parameters and several override relationships. The description covers the central behavioral model, the alternatives, and the cost relationship; the schema fills in parameter-level constraints and default behavior. It doesn't discuss the async/poll flow or the returned data, but the schema-annotated output schema and async doc in the property handle that. All critical decision-making context is present.

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?

Input schema describes every parameter, so the baseline is 3. The description uniquely adds cross-parameter context: it defines Image 1 as the identity slot and Image 2 as the scene slot, gives the default from-panel list, and explains how identity_image/continuity_image relate to the panel ids. That meaningfully exceeds what each individual parameter description provides, earning a higher score.

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's opening 'Add the next panel' names a specific action upon a specific resource, making the tool's purpose immediately recognizable as continuation, not creation or regeneration. It does not explicitly contrast with siblings like regenerate_panel or create_story, but the defaults-and-overrides framing clarifies its role. A direct sibling comparison would push this to a 5.

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 practical when-to-use guidance: 'Override via manga.list_panels' shows the recommended workflow, 'Do not send style_id' gives a concrete exclusion, and 'Same credit costs as create' sets expectations. It implicitly says this is for adding the next panel, but it stops short of explicitly stating when to prefer this over regenerate_panel or create_story. That missing explicit alternative comparison keeps it from a 5.

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