Re-send only the missing or corrupt parts

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

Goes well beyond the annotations: matched parts are left untouched, a zip layout mismatch replaces nothing and returns a corrective error, an encrypted set requires a password that is not stored, and still_needed reports residual gaps. That is exactly the destructive-scope and failure-mode detail the destructiveHint=false / idempotentHint=true annotations cannot convey.

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 behavior and every sentence carries real information – scope, zip caveat, password, return field. The final still_needed sentence feels appended rather than integrated, a minor structural wrinkle in an otherwise tight paragraph.

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?

There is no output schema, so the description must explain returns, and it does (still_needed for remaining gaps, an error message for zip mismatch). Combined with annotations covering write/idempotency and full schema coverage, an agent has everything needed to call this 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 100%, so all four parameters are already documented (parts as folder/one part/all parts, original, password, part_numbers). The description mainly restates those roles ('or the part_numbers you list', 'An encrypted byte set needs password') without adding format or edge-case guidance beyond them, so the baseline of 3 applies.

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 first sentence names a specific verb ('rewrite') and a precisely scoped resource ('only the parts that verify reports as missing or corrupt'), plus the optional override. That scope cleanly separates it from siblings like split_* (which create parts) and verify (which only reports).

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?

It states the precondition clearly ('given the original file and an existing part set') and the reason to pick it over a full re-split ('so you can upload just the replacements'). It also covers the failure branch – a mismatched zip layout means a full re-split is required. It never names the sibling tools (verify, split_zip, rebuild), so the routing is implied rather than explicit.

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