generate_captions

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

Annotations already flag readOnlyHint=false and openWorldHint=true, and the description adds the critical non-obvious context that calls consume AI Caption Assist quota and produce suggestions only. It does not say whether quota is charged per call or per platform, nor whether repeated calls re-consume quota (relevant given idempotentHint=false), which keeps it short of a 5.

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?

Three tightly written sentences with zero filler. The capability statement comes first, followed by cost/output behavior and then the handoff instruction, which is the right order of priority.

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 brand-voice object and no output schema, the description covers purpose, cost, and handoff well but leaves the caller without any sense of the returned suggestion shape or how mode=adapt differs operationally. It is adequate for routing, not for confident invocation.

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 15 parameters and only 33% schema description coverage, the description needs to carry most of the semantic load, but it only weakly implies multi-platform input ("one or more social platforms"). It explains nothing about mode, tone, hashtag_strategy, brand voice, or the preservation flags, so the majority of undocumented parameters remain unguided.

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: "Generate or adapt AI caption suggestions for one or more social platforms." It distinguishes the two modes (generate/adapt) and explicitly separates itself from post creation, so an agent can tell it apart from create_post or generate_image without opening a 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?

It states both the when-not ("returns options only; it does not create or schedule posts") and the follow-up alternative ("pass it to create_post or create_posts_batch"). This gives an agent a complete workflow boundary rather than leaving sequencing to inference.

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