Verify Delivery Conformance

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

The annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is clear from structured data. The description goes beyond that by stating the tool uses ffprobe and optional EBU R128 analysis, and that it returns pass, fail, or not_evaluated per check. It also clearly declares a limitation: the verification has no bearing on Premiere render lineage or visual approval, which adds transparency beyond the 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 a compact three-sentence structure that front-loads the core action (verify a local exported file against an explicit delivery contract), then adds the verification method and the result states. The limitation statement is useful and not redundant. It earns a 4 rather than 5 because the phrase 'Verify a local exported file against an explicit delivery contract' partially repeats the tool name, but nearly every additional word adds value.

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?

With 17 parameters, a 100%-covered schema, an output schema present, and safety annotations set, the description only needs to add the interpretation logic and limitations. It clearly states that checks return pass, fail, or not_evaluated, which is important contextual behavior. It is slightly less complete in that it doesn't explain how to interpret aggregate results or how not_evaluated might arise (e.g., when checks aren't requested), but the output schema may cover this 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?

The input schema achieves 100% coverage with detailed descriptions on all 17 parameters, so the schema already carries the semantic load. The description adds no new parameter-level information beyond its statement that it's checking against a delivery contract. Baseline 3 is appropriate because schema_description_coverage is high and the description does not need to compensate.

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 clearly states that this tool verifies a local exported file against a delivery contract using ffprobe and optional EBU R128 analysis. It also specifies the output states (pass, fail, not_evaluated per check), which removes ambiguity about what the tool actually does. It differentiates itself from related tools like verify_delivery_file by explicitly noting it doesn't prove Premiere render lineage or visual approval.

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 establishes a concrete use case: verifying an exported local file against an explicit delivery contract. It also sets expectations by saying what it does not do (prove Premiere render lineage or visual approval), which helps an agent avoid misusing it for those purposes. However, it does not explicitly name alternative tools like analyze_loudness or verify_delivery_file for related but different checks, so it misses the full when-to-use versus alternatives guidance.

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