download_remote_file

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

Annotations are sparse in substance (readOnlyHint=false, idempotentHint=true) and the description carries the real weight: it discloses the auth mechanism (Keychain credentials), the exact local destination pattern (~/.deployctl/downloads/<project>/<environment>/), that the response exposes local_path, that trailing lines are returned inline with secrets redacted, and the two refusal conditions. None of that is recoverable from the annotations and it is consistent with readOnlyHint=false (a local write occurs).

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?

Three sentences, front-loaded with the action and path example, then destination/return behavior, then the refusal guardrails. No sentence restates the name or the schema, and each clause adds new 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?

There is no output schema, so the description must explain the return — and it does: local_path plus inline tail lines with redaction. Combined with the destination path, credential source, and refusal rules, an agent has everything needed to call it once and interpret the result without a follow-up.

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 earns an increment by tying tail_lines to observable behavior ("the last lines are returned inline") and by surfacing the max_bytes refusal as a semantic consequence rather than just a field. It does not add format or syntax detail for remote_path or environment beyond what the schema already states.

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 and resource ("Download one file ... from the remote server") and immediately scopes it with an example path plus the constraint that directories are refused. The combination of "one file" and the path example makes it unambiguous versus a bulk or directory-listing operation like browse_remote_directories.

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?

It states the context of use (retrieving a single remote file with Keychain credentials) and gives exclusions in the form of refusals: directories and files over max_bytes. It also names the downstream step (local_path readable with a file tool). What it never states explicitly is how to obtain a valid remote_path — that routing to browse_remote_directories appears only in the parameter schema, not the description.

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