create_post

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

Annotations only indicate non-read-only and non-destructive behavior, so the description carries the burden of explaining effects. It discloses the default draft state, exact content_format handling (raw HTML vs escaped text), the lack of Markdown and image upload, and the silent discarding of customMetaData. These are behavioral traits well beyond what the annotations provide, with no contradiction.

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?

Every sentence earns its place. The core purpose is front-loaded, and the description uses short paragraphs to cover publishing flow, content formatting, and important Blogger limitations without fluff or repetition.

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?

Given the tool has 7 parameters, several subtle behaviors, and a sibling workflow (publish_post), the description is complete: it covers the default draft, how to publish, content format semantics, unsupported features, and metadata limitations. The output schema exists, so the agent can learn return shape elsewhere. Nothing essential for correct invocation is missing.

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%, but the description compensates for the non-obvious parameters: draft is explained as a default true with explicit publication guidance, and content_format is fully specified ('html' passes content untouched; 'text' escapes and wraps in paragraphs). It also clarifies constraints on content (no Markdown, no image upload, img must be absolute public URL). Remaining parameters like blog_id, title, labels, and reader_comments are self-evident from the schema.

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 'Create a post' — a specific verb and resource — and immediately clarifies that it creates a DRAFT by default. This distinguishes it from publishing-related siblings like publish_post and from update_post. The purpose is unambiguous.

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 description gives explicit usage guidance: publishing is a separate step via publish_post, and draft=False should only be used when a human has explicitly requested immediate publication. It also warns that Markdown and image upload are unsupported, helping an agent choose appropriate content. This is clear when-to-use and when-not-to-use guidance.

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