rec_profile_start

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

Annotations cover the safety profile (readOnly=false, idempotent=true, destructive=false), so the description only needs to add context, and it does: one recording per (mode, cycle_ms) group, the generated naming scheme, and that inline triggers take precedence over the profile's. It omits cost/resource implications of starting N recordings, but the added behavior is substantial.

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 dense clauses, front-loaded with the core action before the grouping rule and lifecycle routing. Every sentence carries information; the syntax is terse but not padded.

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 and the description already notes that recording ids are returned, so return-value explanation is not owed. It connects start to stop/stats/export lifecycle tools and explains grouping, leaving mainly the four optional parameters undocumented against a 0%-coverage schema.

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% across 5 parameters, so the description carries the entire burden and only partially delivers. 'Triggers given here override the profile's' loosely covers start_when/stop_when, and 'name' is inferable from rec_profile_stop(name), but duration_s and max_events are never explained, and no parameter is named directly.

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: 'Start recording a saved profile', which separates it from the generic rec_start and from rec_profile_save/list/get/delete siblings. The naming scheme '<profile>/<mode>@<cycle>' further pins down what gets created. It does not explicitly contrast itself with rec_start, so a 4 rather than 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?

Gives clear downstream routing: rec_profile_stop(name) stops the whole set, while rec_stats/rec_export operate per recording id. It also notes local triggers override the profile's, which clarifies the start-vs-profile-config decision. No explicit when-not-to-use or comparison to rec_start, but the context is actionable.

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