Reply with media

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

Rich behavioral disclosure beyond the minimal annotations (readOnlyHint=false, openWorldHint=true): if upload fails, STOP and do not post a text-only substitute; requires confirm=true; cost details (~$0.015/post, ~$0.20 with links); and 'Warn before posting links.' This fully compensates for the sparse annotations and gives the agent the safety and failure semantics it needs.

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-loaded with the core purpose in the first sentence, then terse constraint clauses. Every sentence adds information (failure policy, confirm requirement, access tiers, cost, link warning). Slightly dense given the 17% schema coverage, but nothing is wasted for a composite tool.

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?

Complete on the behavioral side: failure handling, confirmation, access restrictions, pricing, and link-warning policy are all covered. The main gap is the unresolved media-parameter ambiguity (media vs media_ids vs media_url), which matters for a tool whose entire point is attaching media. No output schema exists, but for a write-only post tool that's acceptable.

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 schema description coverage at only 17%, the description must compensate for undocumented parameters. It adds meaning to confirm ('Must be true') and implies in_reply_to_tweet_id as the reply target, but it never clarifies the semantics of the three overlapping media parameters (media vs media_ids vs media_url) — a real gap for an agent deciding how to attach media. Partial compensation only.

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 'Composite: upload media (if given) then reply,' stating a specific verb (reply), resource (tweet), and the composite workflow. This clearly distinguishes it from the sibling x_organic_reply (text-only) and x_organic_upload_media (upload-only). An agent can tell exactly what this tool does 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?

Provides concrete usage conditions: self-serve replies only succeed when @mentioned or quoted, enterprise is unrestricted, and self-replies serve as the intended thread mechanism. It also flags when to warn before links. However, it doesn't explicitly contrast with x_organic_reply or x_organic_upload_media as alternatives, leaving the composite-vs-two-step decision implicit rather than stated.

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