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

Annotations declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, covering the safety profile. The description reinforces this with valuable context: 'Does not spend credits or queue a job,' which tells the agent the side-effect profile. It does not add rate limits, auth requirements, or latency expectations, so it falls slightly short of a 5.

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 tight sentences with zero waste. The purpose is front-loaded, the behavioral constraint follows, and the routing instruction comes last.

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?

Complete for a read-only estimation tool. The description establishes purpose, side-effect profile, and sibling relationship; the schema and annotations cover parameters and safety. With an output schema present, no return-value explanation is needed.

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 100%, so all four parameters are fully documented in the schema, including the enum for targetResolution. The description adds no parameter-level detail beyond what the schema provides, making the baseline 3 appropriate.

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+resource: 'Estimate ByteDance upscale eligibility and credits for one stored video.' Explicitly distinguishes from the sibling media_upscale by noting it 'does not spend credits or queue a job' and instructs calling it 'before media_upscale.'

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?

Explicit sequencing guidance: 'Call this before media_upscale' names the alternative and the condition that selects it. The agent knows exactly when to use this tool versus the actual upscale tool, with no exclusions left to inference.

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