get_attachment

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explicitly reveals that the tool only returns locally-archived bytes, never fetches from WhatsApp, requires explicit per-message approval, and is subject to an operator allowlist. These are meaningful behavioral traits that go beyond the input schema.

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 two sentences long, front-loaded with the primary action, and every clause contributes meaning (approval requirement, no network fetch, local-only). There is no redundancy or fluff.

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 tool is simple with 4 parameters and no output schema. The description covers the essential preconditions (approval, allowlist) and core behavior (local-only, no fetch), which is sufficient for an agent to decide when to invoke it. However, the exact return format (inline base64 vs. local path) is only implied through the includeBase64 parameter, not spelled out in the description.

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?

The schema already provides descriptions for 'approved' and 'includeBase64', covering half the parameters. The description reinforces the requirement for 'approved' but does not explain 'id' or 'chatId' beyond their self-evident names. Since schema coverage is exactly 50%, not 'low', the baseline of 3 is appropriate; the description adds minimal extra parameter meaning.

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 ('Return') and a precise resource ('an approved attachment's locally-archived bytes'), clearly distinguishing it from siblings like list_attachments (which only lists) and get_message (which retrieves messages). The scope is further clarified by 'approved', 'local', and 'Never fetches from WhatsApp'.

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 states the key precondition ('Requires approved: true') and mentions the operator allowlist, giving clear context for when the tool can be invoked. It also implies that this tool is for already-downloaded data ('Never fetches from WhatsApp'), but it does not explicitly name sibling alternatives like list_attachments for finding attachment IDs, so it falls short of a 5.

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