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

Adds substantial context beyond annotations: the code targets a published quiz, repeated calls with unchanged settings return the cached file instead of rebuilding, and every build consumes tariff quota. These quota and precondition behaviors are not in the annotations. It stops short of describing the returned artifact's form, and the caching claim sits in mild tension with idempotentHint=false, though the 'force' parameter explains why that flag is false.

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 action semantics and the routing constraint (published-only, no logo upload here) are front-loaded before the caveats. The opening list of use-cases ('sticker', 'slide', 'flyer') is illustrative but adds little operational value, making it slightly longer than strictly necessary.

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 an 8-parameter mutation tool with no output schema, the description covers the important gaps: preconditions, quota cost, caching behavior, and the fact that logo upload is out of scope. Only the exact return payload (file/link) is left implicit, which is minor.

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% and each parameter already documents type, enum, range, and defaults (e.g. size 100–1000, format png default). The description adds no per-parameter syntax beyond the generic word 'settings', so the schema does the work; baseline 3 applies.

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?

States specific verbs and resource: shows the current code/settings, builds a new one (generate), and removes the center logo (delete_logo), all scoped to a quiz's QR code. An agent can distinguish this from siblings like upload_workspace_logo or update_quiz_settings without opening the schema.

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?

Gives clear when/when-not: only for published quizzes (unpublished is rejected), and explicitly says logo upload must be done elsewhere ('это делают в кабинете'). It names a condition rather than a specific sibling tool name, which is slightly less actionable but still routes the agent correctly.

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