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

Far beyond the annotations: 10 second fetch timeout, max 3 redirects, public http(s) only, 1 MB fetch cap, delimited-text-only validation (PDFs refused), 256 KB request body cap, and per-token persistence between calls. The gap is the destructiveHint=true annotation — the description never says what an upload with an existing name does to the prior file, nor does it explain the idempotency the annotations claim.

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 critical constraint — upload once, pass `name` as `path` downstream — is front-loaded, and the three-way content choice follows immediately. It is dense and sentence-heavy, but nearly every clause carries a limit or exception an agent would otherwise get wrong.

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?

Complete on inputs and on the downstream workflow, including the caps that force chunking a large export by month, which is exactly the trap an agent would hit. With no output schema, however, the description never says what comes back (a confirmation? the stored name? a file listing?), which is the one thing an agent must guess.

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 coverage is 100%, so the schema already documents all four parameters, which sets the baseline at 3. The description does add real value on top (mutual exclusivity, header row required, why base64 exists), but it stops short of adding anything the schema descriptions don't already imply.

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?

Specific verb and resource ('Send a bank export to this hosted endpoint') with the crucial reframing that there is no filesystem, so the file is uploaded once and referenced by name in statement_import. This cleanly separates it from statement_import, bank_files and statement_export without opening their schemas.

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?

States the selection rule explicitly — 'exactly one of content, content_base64 or url' — and gives the conditions that pick each: plain text/CSV is the normal case, base64 for UTF-16 Excel exports, url recommended above ~10 KB instead of pasting base64. It also routes lifecycle questions to the siblings bank_files and bank_delete_upload.

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