s3_get_object

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

Annotations already declare destructiveHint=false, openWorldHint=true and readOnlyHint=false; the description adds real value by explaining the atomic temp-sibling-file write, parent-directory creation, and that a failed transfer leaves existing files untouched, plus that no B2/remote data is mutated (which explains why readOnlyHint is false despite the read nature). It does not cover auth requirements or error behavior for missing keys/versions.

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 primary constraint (small object inline) is front-loaded before the alternative modes, and every clause carries information. The saveToPath sentence is long and clause-stacked, which slightly hurts scanability but not correctness.

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?

With no output schema, the description carries the return-format burden and does so: base64 inline with a hard size cap, vs. bytes written to a local path. It also covers the side-effecting local write and the recommended bulk-download path, leaving nothing essential unanswered for correct invocation.

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 baseline is 3, but the description adds meaning beyond the schema's 'save the file to this local path' by spelling out atomic replacement, directory creation, and failure semantics for saveToPath, and by tying the ≤1 MiB limit to the inline mode. Range and versionId are left to the schema.

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?

States a specific verb and resource (read an object) and immediately bounds it two ways: inline for objects ≤1 MiB returned as base64, or streamed to a local path via saveToPath. It names the intended payloads (manifests, sidecars, configs) and distinguishes itself from siblings s3_get_presigned_url and, implicitly, s3_head_object.

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?

Explicit routing: use inline for small inspectable objects, saveToPath for any size, and 'For real object data, generate a GetObject URL with s3_get_presigned_url' with the rationale (bytes never pass through server or model context). This is a clear when-to-use / when-to-use-something-else rule.

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