Stage Take Note

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

No annotations exist, so the description carries the full burden. It does disclose meaningful behavior: writes land in the take's meta.json, the default sender is 'agent', and 'at' is measured on the take's clock. However, it is silent on whether labeling overwrites a prior label, whether notes append or replace, and whether permissions or an active take are required.

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?

A single dense sentence that front-loads the two primary actions (name / note) and embeds parameter hints inline rather than in a trailing list. It is efficient, though the parenthetical nesting makes it slightly harder to scan than it could be.

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 explained. The remaining shortfall is the unexplained required parameters and unspecified overwrite/append semantics for a mutation tool with zero annotation coverage; an agent could call it but might not predict the state change.

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 0%, so the description must supply meaning, and it usefully defines four of the six parameters: label (what the person called it), note, at (seconds on the take's clock), and sender (default 'agent'). The two required parameters, scene and take, are only implied by the tool's domain, leaving a real but modest gap.

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 specific operations on a specific resource: naming a take via label and/or attaching a note at a timecode, persisted in the take's meta.json. This distinguishes it from adjacent tools like stage_note and stage_voice_note by naming the artifact it writes to and the sibling that reads it back (stage_takes). It stops short of a crisp one-line 'what this is' statement, so not quite 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?

The 'and/or' framing plus the pointer to stage_takes(query=) tells the agent this is the write side of a note/label pair and how it is retrieved later. It gives clear usage context but never states a negative condition (e.g. when to use stage_note or stage_voice_note instead).

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