still_package

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

With no annotations provided, the description carries the full burden and does disclose meaningful behavior: the ordered workflow steps, that dry_run returns only a planned graph, and that grading runs by default (apply_grade default True). However it never states that the tool writes files into output_dir (a mutation with side effects), nor anything about permissions, failure modes, or what the cohesion gate does when it fails.

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 pipeline summary is front-loaded in the first line, with parameter documentation following in a clean, conventional Args block. Every line is relevant and there is no filler, though the Args block is purely descriptive rather than adding deeper meaning to each field.

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. For a seven-parameter composite workflow with zero annotations, the description covers the flow and every parameter but leaves the cohesion gate's semantics, failure behavior, and the tool's write side effects unaddressed, which is a notable gap at this complexity level.

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 schema provides no field-level guidance, yet the description documents all seven parameters, including that establish/beats/output_dir must be absolute paths and what dry_run, apply_grade, lut_path, and signal_mode control. The only weakness is that signal_mode is described only as 'Signal-alignment LUT mode' without clarifying the boolean semantics or its interaction with lut_path.

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 states a specific resource ('Multi-still package workflow') and the concrete pipeline it runs ('edit beats → match → grade → cohesion gate'), which maps cleanly onto the sibling tools still_match, still_grade, and still_gate. An agent can tell this is the composite orchestrator rather than any single step, though the description never explicitly says it supersedes those siblings.

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?

Usage is only implied: the pipeline order suggests this tool runs the whole match/grade/gate sequence in one call, so an agent can infer it's for packaged multi-still output. There is no explicit when-to-use, when-not-to-use, or instruction to prefer this over calling still_match/still_grade/still_gate individually, and no prerequisites are named.

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