save_and_present

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

With no annotations, the description carries the full burden and it discloses a lot: the tool writes a timestamped folder to disk, refuses without `pack`, and returns `SHOW_THIS_TO_THE_USER` and `preview_html` with explicit handling instructions. It is slightly less clear about failure modes beyond refusal and does not state whether existing files are overwritten, but timestamped folder naming implies preservation.

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 dense and logically ordered: purpose, precondition, return values, file inventory, report contents, then meta guidance. A few statements, such as 'when pack ... is supplied' after already declaring pack required, are redundant, but nearly every sentence contributes useful workflow or behavior information.

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 12-parameter tool with no annotations and no output schema, the description is unusually thorough about generated files, return values, and workflow dependencies. It is still incomplete because it never defines the required `slug` and `html_body` arguments, and it gives no guidance on how to populate the JSON-LD and presentation-related optional parameters.

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 coverage is 0%, so the description must compensate. It does explain `meta` (required keys, origin from build_schema) and `pack` (required source, contents, missing-five warning), and notes that canonical_url and image_url are read from meta when omitted. However, the two required parameters `slug` and `html_body` are never described, and most simple optional parameters such as title, language, image_path, description, json_ld_faq, and json_ld_article receive no explicit semantic explanation.

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 opening line states a concrete action: 'Write the finished package to disk and hand the post over.' It then elaborates with a specific file inventory and the exact user-facing outputs, so an agent can tell this is the final save-and-present step and not a drafting or schema-building tool. It also situates itself as 'Step 11', which separates it from siblings like write_blog_post and build_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 description gives an explicit precondition: `pack` from build_publishing_pack is REQUIRED and the tool refuses without it. It names the owning tool, lists what it supplies, and warns that skipping it yields a package missing the permalink, tags, banner URL and image prompt. It also instructs the agent to pass the `meta` dict returned by build_schema, making the call sequence unambiguous.

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