Turn raw material into post drafts

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

Rich behavioral disclosure well beyond annotations: grounding claims in verbatim quotes, deterministically dropping unquotable claims, planning different angles per platform, running length/groundedness/originality gates, landing PENDING, never publishing, returning 202 with ingestId and polling via get_source_status, plus detailed style rules. No contradiction with annotations.

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 description is long but information-dense. Every sentence contributes: process, guarantees, async behavior, style guide, and safety. It is front-loaded with a clear one-liner. Slightly run-on in places but justifiably detailed for a complex 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?

For a complex async tool with no output schema, the description covers lifecycle (202 + ingestId), polling, failure modes (EMPTY, FAILED), platform constraints, style expectations, and capability safety. It even cross-references get_source_status and list_posts. Very complete.

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 covers 83% of parameters well. Description adds value by explaining the relationship between text and urls ('give it one or more URLs, pasted text, or both' and use text for paywalled/JS-rendered). It also adds platform behavior (only connected platforms) and clarifies scheduleHint is applied at approval. Minor gaps remain for brand/title but schema already documents them.

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 clearly states a specific verb and resource: 'Turn RAW MATERIAL into platform-native post drafts.' It distinguishes from siblings like create_drafts and schedule_post by emphasizing it fetches/extracts URLs or text, drafts in native format, and never publishes. The scope is well-defined.

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 clear usage context: when to use with URLs, pasted text, or both; when to use text (paywalled/JS-rendered); and that only connected platforms are drafted for. It doesn't explicitly name alternative tools or say 'use this instead of create_drafts', but the source-based workflow is implied clearly enough.

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