Save email attachments from a specific message to disk, either all or a selected one, and get the saved file paths.
Salva anexos de um e-mail em disco. index=-1 salva todos; caso contrário salva só o anexo indicado (índice conforme read_email). Retorna os caminhos gravados.
| Name | Required | Description | Default |
|---|---|---|---|
| uid | Yes | ||
| index | No | ||
| folder | Yes | ||
| dest_dir | No |
| Name | Required | Description | Default |
|---|---|---|---|
| result | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden and does disclose the main side effect ('Salva anexos ... em disco'), the conditional index behavior, and the return value ('caminhos gravados'). However, it does not mention behavior on invalid indices, missing attachments, destination-directory handling, or potential overwriting.
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?
Three short sentences deliver the tool's purpose, special-case behavior, and return value without unnecessary prose. Every sentence adds useful information and the key behavior is front-loaded.
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?
The description is adequate at a high level but incomplete for a tool with four parameters and no annotations. It fails to specify valid folder/uid values, dest_dir semantics, failure behavior, or prerequisites, so an agent may not be able to invoke it correctly without external context.
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 undocumented parameters. It explains the meaning of index (-1 versus a specific index per read_email), but folder, uid, and dest_dir are left to inference from their names, and the dest_dir default is not described.
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 states a specific verb and resource: it saves email attachments to disk, with a clear distinction from body-reading or message-management siblings. The phrase 'index=-1 salva todos' adds scope and identifies the special case, making it easy to tell from read_email or get_raw_email.
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?
No explicit guidance is given for when to use download_attachment versus alternatives such as read_email or get_raw_email. The only hint is 'índice conforme read_email', which clarifies index alignment but not selection context or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.