Record Eos Cue

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

Annotations already mark this as destructive and non-read-only, but the description adds critical context beyond that: it explicitly warns that the tool OVERWRITES existing cue data with no separate confirm step, reveals that it uses the Eos command line under the hood, explains the 'Cue List Does Not Exist' error condition, and notes rate limiting. It also explains the confirm parameter's preview behavior. No contradiction with annotations.

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 description is appropriately detailed for a destructive tool, yet every sentence serves a purpose: warnings, prerequisites, error handling, verification, and parameter semantics. The structure (overview, mechanism, prerequisites, args, rate limit) is logical and front-loaded with the most critical warning. No redundant filler.

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 mutation tool with no output schema, the description is exceptionally complete. It covers the action, when to use, destructive consequences, prerequisites (existing cue list), failure modes and workarounds, post-invocation verification via eos_get_status, and rate limiting. The agent is fully equipped to invoke this tool safely and 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?

Although the schema covers 100% of parameter descriptions, the description adds meaningful semantics: it explains that cue_list must already exist, provides cue_number format examples, clarifies that confirm must be explicitly true to execute, and describes the preview behavior when false. It also mentions rate limiting that affects parameter usage. This goes well beyond the schema.

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 opens with a specific verb+resource: 'Record the current live state into a cue.' It clearly distinguishes from sibling tools like eos_fire_cue (firing a cue) and eos_select_cue (selection), and explicitly names the underlying Eos command. The scope and behavior are unambiguous.

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 description provides explicit when-to-use and when-not-to-use guidance. It states the tool will overwrite existing cue data and advises double-checking cue numbers on a real rig. It also names alternatives: use eos_send_raw_command to create a cue list first or record the first cue, and use eos_get_status to verify success. This gives the agent clear decision context.

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