rec_profile_start

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

Annotations only supply the safety profile (readOnly=false, idempotent=true, destructive=false), so the description earns credit for adding real behavior: triggers supplied here override the profile's, the return value is recording ids, and the align mode coordinates a shared start cycle across groups so all files cover the same window (even citing the D29 ~160 ms observation). It omits failure/edge behavior — e.g. what happens if the profile is unknown or a recording is already running.

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?

Purpose and the naming/grouping rule are front-loaded, which is good, but the second sentence is a dense run-on whose parenthetical '(default, several groups, no start_when)' is cryptic and does more work than it can bear. Most sentences earn their place, yet the align explanation could be far tighter for the same 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?

An output schema exists, so return values needn't be detailed (though it does mention returning ids). The real gap is coverage of a 6-parameter mutation-ish tool at 0% schema description: three parameters and all error/permission behavior are undocumented. Given the tool's complexity, the description is a useful but incomplete operating manual.

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 carries the full burden, and it only partly delivers. It explains align (default, meaningful only with several groups and no start_when) and gives duration_s meaning under align, and it references start_when in passing. The required param name, plus stop_when and max_events (default 5,000,000), get no explanation at all, leaving three of six parameters opaque.

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+resource ('Start recording a saved profile') and adds distinctive detail: one recording per (mode, cycle_ms) group with the naming pattern '<profile>/<mode>@<cycle>'. An agent can tell this apart from ad-hoc rec_start. It stops short of explicitly contrasting itself with the sibling rec_start, which is the only thing keeping it off a 5.

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 names the complementary tools ('rec_profile_stop(name) stops them together, rec_stats/rec_export work per id'), which routes the agent for follow-up calls and implies the lifecycle. However, it never says when to prefer this over sibling rec_start or rec_capture, nor any prerequisite (e.g. a saved profile must already exist). Usage is implied rather than stated.

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