preview_review_log

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

With no annotations, the description carries the full burden and does disclose meaningful behavior: the 1-10 scoring scale per dimension, the conditional problem report, and the hard gate that refuses upload unless all scores are 8+ on the MD5-matched final file. It stops short of describing retry limits or what a rejected log returns, but the workflow constraints are unusually well surfaced.

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?

It is a single dense block that front-loads the core logging action before adding workflow and gating detail, with no filler sentences. The run-on structure and abrupt parentheticals reduce readability slightly but every clause carries information.

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 not be explained, and the description covers the nested scores/problems structure plus the gate conditions an agent needs to act correctly. Given the tool's complexity and zero schema description coverage, it is nearly complete, with only app_dir semantics and failure behavior left implicit.

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 must compensate, and it does: 'file relative to the app' explains the file path convention, the scores map each key to hook/readability/motion/variety/brand/music with a 1-10 range, and problems is defined as the 3 worst issues with [{t, issue}] timestamps. Only app_dir is left implicit, keeping it below 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?

The description states a concrete verb and resource (log one self-review round of a final preview) and enumerates the score dimensions, so the agent knows exactly what is being recorded. It also names the related sibling preview_upload, aiding differentiation. The phrasing is somewhat dense and buries the logging action inside a workflow narrative, keeping it short of a 5.

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 conveys the workflow context ('Fix, re-render, re-review until every score is 8+') and hints at the gating relationship with preview_upload, which implies when the tool belongs in the cycle. However, it does not explicitly contrast with the other review siblings (preview_check, preview_review_sheets, preview_brief) or state when not to use it.

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