fetch_file

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

Annotations already indicate this is a write-like operation (readOnlyHint=false) and not destructive (destructiveHint=false). The description adds valuable behavioral context: it is a bounded download, returns a transfer job, requires budget_bytes for large files, and is not implemented in this build (returns E3). This goes beyond the annotations and helps the agent set expectations.

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?

Two sentences, front-loaded with the core action and return type, then the budget_bytes caveat and the not-implemented warning. No wasted words. It could be slightly more structured, but it is efficient and readable.

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?

Given the output schema exists and the annotations cover safety, the description is fairly complete: it states the action, the return type, the budget_bytes condition, and the unsupported status. It does not explain what a transfer job is or how to poll it, but sibling tools get_transfer_status and cancel_transfer exist, so the context is inferable. The missing parameter semantics for include_index and verify_checksum are minor gaps.

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. It mentions budget_bytes and the file+index concept, but does not explain the other parameters (include_index, verify_checksum) or the FileRef fields. The description adds some meaning (bounded download, budget_bytes) but leaves most parameter semantics to the schema, which has no descriptions for the top-level parameters.

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 ('Start a bounded download') and resource ('a file (and index) to the local work dir'), and distinguishes it from sibling read tools by noting it returns a transfer job. It is clear but does not explicitly name a sibling alternative, so it loses a point for differentiation.

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 gives clear context: it is for bounded downloads, and files above the default limit need budget_bytes. It also warns that the tool is not implemented in this build and returns error code 'unsupported' (E3). It does not explicitly say when to use an alternative like get_reads or get_sequence, but the transfer-job framing implies it is for materializing files rather than streaming data.

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