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

Annotations only supply the safety profile (not read-only, not idempotent, non-destructive, open-world). The description adds genuinely new behavior: it consumes AI Caption Assist quota (a metered side effect consistent with readOnlyHint=false) and yields options rather than persisted artifacts. It does not disclose failure modes when quota is exhausted or whether results are cached across identical calls.

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?

Two sentences, no filler, and the capability statement is front-loaded ahead of the boundary caveat. Every clause is load-bearing.

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 15-parameter tool with a nested manual_brand_voice object, three enums, and no output schema, the description is far too thin. It never explains the generate-vs-adapt workflow that most parameters depend on, and gives no hint about what the returned caption options look like or how many are returned per platform.

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 0% across 15 parameters, so the description carries the full burden and largely fails it. 'Generate or adapt' faintly gestures at the mode enum and 'one or more social platforms' at platforms, but the critical mode/source_caption/source_platform coupling, tone, hashtag_strategy, brand-voice object, and the preserve_* flags are entirely unexplained.

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 gives a specific verb pair and resource ('Generate or adapt AI caption suggestions') plus scope ('one or more social platforms'). The second sentence immediately demarcates it from the create_post family, so an agent can distinguish it 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?

The clause 'it does not create, draft, schedule, or publish posts' is an explicit when-not boundary that routes agents away from create_post/create_posts_batch, and 'returns options only' clarifies the output-only nature. It lacks a positive 'use this when you need copy suggestions before drafting' framing and never names the alternative tool, so it stops short of a full 5.

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