sfx_render

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

With no annotations provided, the description carries the full disclosure burden and does so well: it states the output format, the out_dir resolution order (SFX_OUT_DIR env var or ./out), normalization info, and the warning behavior for a missed loudness target. This is rich behavioral context for an annotation-free tool.

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?

One dense, front-loaded sentence that opens with the core purpose before detailing return values and defaults. There is no filler or repetition, and every clause adds information.

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?

The output schema covers return values, and the description adds useful semantic interpretation (feature definitions pointing to the cookbook, warning conditions). However, for a complex tool with a nested open-object parameter, the spec input structure is left under-specified; the 'cookbook' pointer partially mitigates but doesn't close the gap.

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 adds real meaning for out_dir by documenting its default resolution, and hints at spec semantics via the returned features list. But the spec parameter is an open object (additionalProperties: true) and the description never states what fields a SoundSpec requires, leaving a significant 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?

'Render a SoundSpec to a 16-bit mono WAV' is a specific verb+resource+output-format statement that clearly states what the tool produces. It lists the returned artifacts (file path, id, features, normalization info, warnings) which disambiguates it from siblings like sfx_analyze or sfx_play, though it never explicitly names a sibling like sfx_render_preset to contrast against.

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 implies workflow context by noting it returns an 'id for later tweaks', signaling it is the primary creation step in a pipeline. However, it provides no explicit when-to-use guidance, no exclusions, and never mentions alternatives such as sfx_render_preset, leaving the agent to infer selection logic.

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