Save reviewed attachments

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

Adds real behavior beyond the annotations: no overwriting of existing files, repeat calls return the existing job (reinforcing rather than merely repeating idempotentHint), written files survive cancellation, and results carry source/path/checksum. Missing only auth/error behavior.

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?

Four short sentences, front-loaded with the action and its key constraint, each carrying distinct information (idempotency, follow-up tool, cancellation semantics, result shape). Minor redundancy with idempotentHint costs little.

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?

Output schema means return values needn't be explained, and the description usefully covers cancellation and idempotency. But for a write tool with 0% parameter documentation, the unexplained confirm flag is a material gap an agent could get wrong.

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 and does not: plan_id and especially the confirm boolean (default false) are never explained, and the relationship between confirm and executing a write is left entirely unclear.

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?

"Save a frozen attachment plan once" is a specific verb plus resource, and "frozen attachment plan" implicitly ties it to mail_attachments_plan while distinguishing it from mail_save_attachment (per-file). It never names the sibling tools, so the differentiation is inferred rather than stated.

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?

Usage is implied through the workflow chain: save a plan, then poll with tb_operation_status (explicitly named). But no alternative is named (e.g., mail_save_attachment for a single file) and no prerequisite for the confirm flag or plan lifecycle is given.

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