video_workflow_inspect

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

No annotations provided, so the description carries full burden. It explicitly states the tool is read-only, performs integrity checks (hash re-check), and fails closed on malformed receipts. It also describes the output structure and limitations.

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 well-structured with a clear summary, detailed explanation, and parameter description. It is slightly verbose but front-loaded with the key action. Every sentence adds value, though some phrases ('read-only' is repeated) could be trimmed.

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?

Given the single parameter and presence of an output schema, the description provides comprehensive details about what the tool returns: kind, schema_version, tool, versions, status summary, hash report, outputs, warnings, cleanup state, pointers, and limitations. It covers all necessary behavioral context.

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?

With only one parameter (receipt_path) and 0% schema coverage, the description adds essential meaning: it specifies the parameter is an absolute path to a receipt JSON file. This goes beyond the schema which just says 'string'.

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 identifies the tool's purpose: summarizing receipts with a read-only integrity check. It specifies the types of receipts (workflow render receipt, dry-run workflow_plan artifact, layer_plan receipt) and distinguishes from siblings by focusing on inspection.

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 states when to use the tool (for inspecting receipts) and what it does not do (render or modify). It implies not to use it for mutation operations like rendering or planning. However, it lacks explicit when-not-to-use instructions or alternative tool names.

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