object_ls

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

Annotations already declare readOnlyHint, so safety is covered, and the description adds genuinely non-derivable behavior: the truncation envelope, the 'millions of keys' reality, and that `lastModified`/`versionId` can be null when the source had no value. Missing only minor details like pagination cursor absence or ordering.

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?

Front-loads the critical truncation warning before the return shape and arg list, so the most important behavioral fact is read first. Slightly verbose with the inline JSON return snippet, but every sentence carries information.

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 supplies the return envelope shape and null-field caveats, plus per-parameter meaning and the truncation contract. An agent has enough to call it correctly and interpret the result; only deep pagination/ordering semantics are omitted.

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 0%, so the description carries the full burden and largely does: it documents all four params, giving `bucket_name` origin, `prefix` semantics (empty = whole bucket), `limit` default 100 and max 1000, and `target` as a config name omitted for default. This meaningfully exceeds the bare schema types.

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 (list) and resource (objects) plus scope (under `prefix`), and the parenthetical '(never a full walk)' immediately distinguishes it from a bucket-level listing. The 'from bucket_ls' hint ties `bucket_name` to the sibling that produces it, so the boundary against bucket_ls is clear.

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?

Explicitly tells the agent that `truncated: true` is normal and to re-run with a higher limit or narrower prefix rather than treating the page as complete. It gives operational context and remediation but does not name sibling alternatives directly.

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