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

Annotations cover safety (destructiveHint false, idempotentHint true) but not the cost model, and the description adds real value: it spends and reserves nothing, it writes a 24-hour retry record keyed by request_key, and it is free. That also explains why readOnlyHint is false despite no spending. It stops short of describing the output shape or pagination, which is acceptable given an output schema exists.

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 use case is front-loaded, then return semantics, then side effects, then the approval workflow, then a compact 'Not for:' block. It is dense but nearly every clause carries routing or behavioral information; the quoted example phrasings are the only mildly padded element.

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 four-parameter estimation tool with an output schema, the description covers purpose, cost semantics, side effects, approval flow, and exclusions. Nothing needed to select or invoke it correctly is missing.

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 carries the full burden and does it well: range_start/range_end are in seconds with '0 and 0 = the whole video', and request_key is 'any stable string' tied to a 24-hour retry record. project_id is only implied through 'on project_id', so one of four parameters remains lightly defined.

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 verb and resource — it returns the Horizon Units that clipping work on project_id would cost — and explicitly separates itself from the siblings that actually start the job (find_clips, find_moments, clip_range). The opening line 'what clipping a video will cost before anything runs' makes the non-executing nature obvious without opening a schema.

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?

It gives the triggering context ('when the user wants to know what clipping a video will cost'), supplies example user phrasings, and a 'Not for:' exclusion list naming the actual job-starting tools and the edit-cost case. It additionally prescribes the workflow: show the number, wait for approval, pass it as max_hu to the spending tool.

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