Inspection and release operations (doctor, preflight, guardrails, review, publish)

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

Annotations declare destructiveHint=true, readOnlyHint=false, openWorldHint=true and idempotentHint=false, but the description adds nothing about what gets destroyed or which of the 15 bundled operations are destructive versus read-only. In a dispatcher whose operations range from 'capabilities' to 'publish_gate', stating that behavior varies by operation and that the overwrite flag can replace existing media files would be materially useful context the agent cannot get from the schema.

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, zero filler, and the core action statement is front-loaded before the discovery pointers. Nothing is repeated from the schema or annotations.

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?

An output schema exists so return values need no explanation, and the discovery pointers cover the argument gap. However, for a 15-operation destructive dispatcher, the absence of any per-operation risk signal or guidance on the overwrite flag leaves an agent unable to judge which calls are safe without chaining to describe_operation first.

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 description directly addresses the schema's weakest point: params is an opaque anyOf object with only 'The operation's arguments' as documentation, and the description tells the agent to call describe_operation for the full per-operation schema. The overwrite parameter's replace-media semantics are left to the schema, which limits it from a 5.

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?

States a specific verb and resource class: 'Run one inspection/release operation by name' with arguments passed via params. It also distinguishes itself from the sibling discovery tools by naming list_operations and describe_operation, though the phrase 'inspection/release' is broad and the agent must read the enum to learn what actually qualifies.

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 gives a discovery path (call list_operations for required arguments, describe_operation for the full schema) which is genuine usage guidance. It does not say when to call this dispatcher versus directly calling siblings like video_doctor, video_preflight, or video_extract_frame, which also appear as operations inside the enum — that overlap is left unresolved.

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