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

Annotations only flag readOnlyHint=false and destructiveHint=false; the description goes far beyond that. It discloses validation-before-upload behavior, a complete list of validation_error codes and their meanings, the file_not_readable and local_files_disabled errors, return contents, TTL expiry, and the plan requirement (no_active_plan). No contradiction with 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 long but every sentence delivers actionable detail. It opens with the core function and return value, then explains each parameter, lists error codes in a structured way, and closes with integration and error handling. No filler or repetition; the density is justified by the tool's many edge cases.

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 modest 3-parameter tool, the description covers all necessary usage details: parameter selection, size/format constraints, validation errors, return values, expiry, integration with sibling tools, and plan errors. An output schema exists but the description already explains the return fields, so an agent has everything needed to invoke the tool correctly without external resources.

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 coverage is 0%, so the description carries the full burden. It explains label as an optional short note limited to 120 characters, file_path as a server-side path only for local runs, and image_base64 as base64 bytes or a data URL accepted without needing public access. It also links error codes to specific parameter failures (both/neither, bad_base64, etc.), adding semantic meaning beyond the schema's bare property names.

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 ('Upload one reference image and get a reference_id to reuse') and clearly identifies the resource (reference image) and the outputs. It differentiates from siblings by mentioning how the result feeds into tegas_write_scenario or tegas_start_video, and the context of reference images for products, characters, brands is explicit.

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-to-use guidance for the two source parameters: image_base64 for remote agents (image never needs to be public) and file_path only for local/self-hosted runs with server enablement, including the fallback if local files are disabled. It also explains when to re-upload (TTL expiry) and how to pass the returned reference_id to other tools.

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