verify_edit

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

With no annotations provided, the description carries the full burden — and it does well. It discloses that the tool is deterministic, that it returns pass/fail plus diffs, and most valuably, it explains the expected_clip_count gotcha: the parameter is recorded for plan bookkeeping because a single rendered file cannot recover clip count. This prevents a real misuse where an agent assumes the tool verifies clip count from the file.

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?

Three sentences, front-loaded with the core purpose in sentence one, and the clip-count caveat in sentence three earns its place by disambiguating a misleading parameter name. The only slight waste is the abstract label 'deterministic verification bridge,' which adds flavor but little information beyond what sentence one conveys.

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, so that gap is acceptable. But for a 9-parameter tool with zero schema description coverage and no annotations, the description leaves too many parameters unexplained (allow_any_path is especially opaque). It explains the one genuinely confusing param (expected_clip_count) and the overall semantics, but an agent calling with non-default values would still be under-informed.

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 — and it partially does. It explains that duration and resolution are the comparison dimensions, and it gives real semantic meaning to expected_clip_count. However, it leaves several non-obvious parameters undocumented: allow_any_path, duration_tolerance, max_duration/min_duration, and expected_duration vs. the duration bounds are never clarified, so an agent would still have to guess at their roles.

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 action and resource: 'Compare an output file against an expected edit plan (duration, resolution)' and explicitly declares the return type ('pass/fail + diffs'). The second sentence — 'agents can assert plan vs probe results' — ties it to the probe_media sibling, making the distinction between probing (gathering facts) and verifying (asserting against a plan) clear.

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 when to use the tool ('deterministic verification bridge: agents can assert plan vs probe results') and positions it in a plan→probe→verify workflow. However, it never explicitly states when not to use it or names alternatives (e.g., when to use probe_media instead of verify_edit). Usage guidance is implied rather than stated.

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