aether_submit_feedback

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

With no annotations provided, the description carries the behavioral disclosure burden. It usefully reveals the write-like side effect (records rating, reason_code, shipped code, feeds learning pipeline) and mentions the required API key. It does not disclose whether feedback can overwrite prior feedback, idempotency behavior, or error/return behavior, so it is adequate but not rich.

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?

Two sentences with no filler. The core action and key are front-loaded in the first sentence, the briefly important learning context and API key requirement follow in the second. Every sentence earns its place.

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 an 8-parameter mutation-like tool with no output schema and no annotations, the description covers the essential operational context: what it does, what records, the required key, and the intent behind submission. It could additionally explain where finding_id comes from or how failures surface, but the schema already handles the parameter details and the core call scenario is clear.

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 100%, so the schema fully documents all eight parameters. The description adds a small amount of connective context by calling out rating, reason_code, and developerCorrection as the key recorded fields, but it does not meaningfully supplement the existing per-parameter descriptions.

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 specific verb ('Submit') and resource ('developer feedback on a previously returned WCAG fix/artifact') and anchors it to a concrete key ('finding_id'). It clearly differentiates this from the sibling scan/fix/verify tools by focusing on post-fix feedback rather than performing scans or fixes.

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 the tool is used after a fix/artifact has been returned, and notes it is meant to help the pipeline learn from misses. However, it does not explicitly state when not to use it or name sibling alternatives as fallbacks, leaving the timing context inferable rather than explicit.

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