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

Adds context beyond the readOnlyHint annotation: an 'Admin only' access restriction, the fact that already-rendered images are returned so a cache hit can be reused, and the empty-options skip behavior. Return-value detail is left to the output schema, which is acceptable given that schema exists.

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?

Front-loads the access constraint, then the two modes, then a compact Args block that maps one line per parameter. No filler sentences; every line supplies routing or argument meaning.

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?

Covers access, both invocation modes, arg formats and cache behavior, and an output schema handles return values. However, the name ('graphics') and description ('formats') diverge enough that an agent may be unsure what is returned, and the relationship to marketing_render (presumably the write/render counterpart) is never addressed.

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?

With 17% schema coverage across 6 params, the description carries most of the burden. It does well on content_id ('gc:{id} or rd:{uuid}') and status ('live or draft'), but section, language, and format are documented only as 'Catalog filter', which mostly restates the parameter names without adding value; strategy_id is covered only by the schema.

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?

Names the resource (marketing graphics / live formats) and its two distinct modes: per-inbox-item formats or a filtered catalog. That dual-mode framing lets an agent distinguish it from siblings like marketing_inbox, though the verb is implicit and it is not explicitly contrasted with marketing_render.

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 concrete routing: 'For a bot, pass content_id from marketing_inbox' tells the agent where the identifier comes from, and 'Empty options means skip the item' tells it how to react to an empty result. It stops short of naming when to prefer marketing_render or marketing_inbox over this tool.

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