Download a trend recording

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

With no annotations, the description carries the full burden and does a good job: it warns that long recordings take minutes over Bluetooth, describes resume-after-interruption semantics, and enumerates the return payload (file, record count, seconds per record, retries, header). It omits file-overwrite behavior when 'out' already exists and does not discuss permissions or failure modes beyond timeouts.

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 core action and target format lead the description, followed by operational caveats and return shape — a sensible ordering. The parenthetical column list is slightly dense but earns its place by telling the agent what a row contains.

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?

For a six-parameter, file-writing tool with no output schema, the description covers the essentials: what is written, what is returned, latency expectations, and resume behavior. The main residual gaps are overwrite semantics for an existing 'out' path and interaction between `limit` and resume.

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 100%, so every parameter is already documented, and the description's resume note largely restates what the `start` field says. It adds no semantics for `limit`, `max_wall`, or the default-path behavior of `out`, so the schema is doing the heavy lifting.

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 ('Download trend recording `index`') plus the output format (CSV/JSONL) and row shape. It also routes the agent to the sibling `memory` tool to obtain the index, so it is distinguishable from `read`, `query`, and `live` without opening a schema.

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?

Gives clear context: use this to pull a whole recording to a file, and use `memory` for indices. It also documents the resume path ('start' plus the same 'out'). It does not explicitly state when to prefer a sibling such as `read` or `query` for lighter-weight access, so it stops short of full when/when-not guidance.

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