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

Annotations only carry the generic safety profile (readOnlyHint=false, idempotentHint=false). The description adds substantial non-obvious behavior: 'Style locks' warns that style becomes immutable after creation, 'Default async=false returns image_url, story_id, panel_id' discloses the sync/async contract and key return fields, and 'Costs 1/2/5 credits by quality' surfaces the financial consequence. It also reveals that identity_image/reference_image becomes 'Image 1' — a stateful placement detail no annotation could convey.

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 sentences deliver the entirety of the workflow in roughly 55 words, with the core action front-loaded. Every sentence earns its place: scope, required/optional inputs, locking behavior, async contract, continuation pointer, and cost. No repetition or filler; the structure mirrors the agent's decision sequence.

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 its complexity — an 8-parameter, stateful, credit-consuming tool with an output schema — the description is fully adequate: it covers the start-of-story scope, the prerequisite call, the optional image semantics, the style-lock constraint, the sync/default behavior, cost, and the successor tool. The output schema owns return structure, and the 100% schema coverage handles parameter details, so nothing the agent needs to invoke it correctly 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?

Schema coverage is 100%, so the baseline is 3; the description adds meaning beyond the schema by grouping required vs optional inputs ('Required: prompt + style_id', 'Optional identity_image or reference_image') and by framing identity_image/reference_image as alternative slots for the story's 'Image 1' — a workflow semantic the schema does not state. The credit-cost mapping (1/2/5) is surfaced prominently, though it also appears in the quality param description.

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 and resource ('Start a new private manga (panel 1)'), clearly marking this as the story-creation entry point. It differentiates itself from siblings in the same line: continue_story handles later panels and 'Then manga.continue_story' anchors this tool as the first step. The required inputs (prompt + style_id) are named immediately, so an agent knows exactly what the tool accomplishes.

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 explicit workflow routing: obtain style_id from manga.list_styles before calling, and follow up with manga.continue_story afterward — implying this tool is for the first panel only. It does not explicitly state 'do not use for existing stories' or name regenerate_panel as an alternative, but the prerequisite and successor hints are strong enough to prevent misuse.

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