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

Annotations only declare idempotentHint=false and destructiveHint=false, and the description adds substantial behavior beyond them: it is free but rate-limited, unanalyzed handles are refused rather than fetched, aspect is silently remapped with a response flag, and brandKitAvailable gates whether palette/typography actually ground the brief. That is exactly the kind of context structured fields cannot carry.

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 defining sentence leads with the artifact, then constraints and the create_deck handoff follow in priority order. It is dense but nearly every sentence carries operational information, though the brandKitAvailable/styleSource passage is somewhat verbose for what it adds.

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 a complex 12-param tool with no output schema, the description still names the key return signals (aspectMappedFrom, styleSource, brandKitAvailable) and explains the downstream contract with antix_create_deck. An agent can call it and interpret the result without further lookup.

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 description coverage is only 25% across 12 params, so the description must compensate. It adds real meaning for accountHandle (must be audited first) and aspect (9:16 mapping), but leaves brand, objective, slideCount, voiceDescription, visualReferences, projectId, briefId, and locale unexplained beyond their names and enums, so the gap is only partially closed.

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 first sentence names a specific verb and multi-part artifact (slide-by-slide narrative with headline/body/image brief, caption, hashtags) plus its inputs (topic + audience). It also distinguishes itself from antix_create_deck by stating the result 'feeds antix_create_deck verbatim', so an agent knows the sequencing between the two siblings.

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?

It gives concrete conditions: pass accountHandle only for already-analyzed accounts (refused, never fetched), and 9:16 is accepted then mapped to 4:5. It doesn't compare against alternatives like antix_list_carousel_templates or antix_list_carousel_design_options, so the 'which sibling' routing is only partially covered.

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