Live Rejects

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

With no annotations, the description carries the full burden, and it delivers the key behavioral facts that structured fields do not: retention caps of 50 rejects and 20 underrun bursts, and that results are ordered into two sections. It does not state read-only status or whether history is truncated/pruned per project, but for a diagnostic log read the disclosure 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?

It is dense but front-loaded: the primary payload is described first, the secondary burst data next, then the filter, then the sibling comparison. The nested parenthetical about sound_import/live_track is long but earns its place as actionable next-step context. Slightly long single paragraph with no structural break between the two record types.

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 need not be spelled out, yet the description still previews the fields an agent will need to reason about failures. It covers what is returned, both retention windows, the since filter, and the sibling alternative — everything an agent needs to select and call it correctly.

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 must compensate. It does explain 'since=<bar> keeps those from that bar on', which meaningfully clarifies a bare integer parameter the schema leaves blank. However, the required 'project' parameter gets no explanation at all, leaving half the surface undocumented.

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 names a concrete resource on two axes: rejected renders retained by the engine (last 50) with the bar, deck, track, clip, note/kit pad, reason, and underrun bursts (last 20) with counts and preceding ops. It is clearly distinguishable from live_status, which is explicitly called out as showing only the newest few. It loses a point only because the opener is a noun phrase rather than a clean verb ('retrieve/list'), leaving the action implied.

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 explicitly positions itself against the sibling 'live_status shows the newest few; this is the whole list', which is a genuine when-to-use-this-vs-that signal. It also gives remediation guidance (sound_import then live_track with the same instrument) rather than a precondition for calling the tool, so the routing advice is good but not a full when/when-not statement.

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