Export Aaf

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

All annotations are default false values (readOnlyHint, idempotentHint, destructiveHint, openWorldHint), so they convey almost nothing and the description carries the disclosure burden. The description discloses the single most decision-relevant behavioral fact — calls to this tool will not work on the CEP backend — and adds an authentication prerequisite for the alternative. No contradiction with annotations exists since 'unavailable' does not conflict with any of the default hints. It falls short of 5 only because it discloses nothing about the tool's actual behavior beyond unavailability, though for a dead-end tool that is arguably all that matters.

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 short sentences where every word earns its place. The critical fact is front-loaded ('Unavailable on the CEP backend'), followed immediately by the action directive naming the alternative. Zero waste, no filler, ideal structure for an agent to parse quickly.

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 tool whose only purpose is to divert the agent, the description is complete: it states unavailability, names the replacement, and gives the required version and authentication context for that replacement. The output schema exists, all parameters are schema-documented, and nothing an agent needs to decide whether/how to invoke this tool is missing. Full context for a dead-end redirect.

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% — all 5 parameters (output_path, sample_rate, mix_down_video, bits_per_sample, explode_to_mono) have descriptions in the schema — so the baseline 3 applies and the description need not compensate. The description adds no parameter-level meaning, which is acceptable given the tool is a redirect and the schema already documents every field.

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 explicitly communicates the tool's operational status — 'Unavailable on the CEP backend' — and distinguishes it from the working sibling export_aaf_uxp, which is the sibling differentiation the rubric rewards. It never states the verb+resource ('exports AAF files') explicitly, but the title 'Export Aaf' and the tool name carry that meaning, so an agent can infer the function. Slightly under a 5 because the function itself is only implied, not described.

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?

Provides explicit when-not-to-use guidance ('Unavailable on the CEP backend') and names the exact alternative with its prerequisite: 'Use export_aaf_uxp with an authenticated Premiere 26.3+ UXP bridge.' This is textbook routing behavior — the agent knows not to call this tool and knows exactly what to call instead and under what conditions.

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