prepare_for_submission

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

With no annotations, the description carries the full burden, and it delivers detailed behavioral disclosure: destructive operations are enumerated ('accept all tracked changes,' 'delete all comments'), content-preservation guarantees are stated, refusal conditions are given (protected documents, open in Word), and backup/atomic-save behavior is specified. This is exceptionally transparent for a mutation-heavy operation.

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 adds needed operational detail; there is no filler. The main purpose and scope are front-loaded in the first sentence, and the remaining sentences cover exceptions, reporting, backup, and save behavior without redundancy.

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 six-parameter, no-annotation tool, the description covers intended scope, side effects, safety (content preservation, atomic save), refusal cases, backup semantics, and reporting. An output schema exists, so the description need not enumerate return fields; what remains is complete enough to invoke correctly.

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%, so the description must compensate for the six parameters. It does: backup behavior is described, keep_title is explicitly tied to 'title kept unless keep_title=False,' scrub_metadata is detailed with author/last-modified-by/company, accept_revisions and remove_comments are covered by the opening sentence, and file_path is implied through 'Refuses documents open in Word.'

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 ('Prepare a manuscript for submission') and enumerates the concrete operations it performs: accept tracked changes, delete comments, scrub metadata. This clearly distinguishes it from single-purpose siblings like accept_revisions or delete_comment by framing it as the one-call submission pipeline.

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 phrase 'in one call' plus the explicit list of bundled operations gives clear context for when an agent should select this tool over individual editing tools. However, it does not explicitly name alternatives or state when NOT to use it, such as 'if you only need to accept revisions, use accept_revisions instead.'

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