Preview Review Log

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

Annotations declare a non-read-only, idempotent, non-destructive write; the description reinforces this by describing gating behavior, the MD5-match requirement, and downstream refusal by preview_upload. It does not explain what is persisted or how repeated logs for the same file interact, which is the remaining gap.

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 front-loaded lines: action, when, and return shape. No filler, and the critical gating constraint arrives early enough to affect the call decision.

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 four parameters, high schema coverage, and an existing output schema, the description covers purpose, sequencing, pass/fail gate, and consequence of failure. The duplicated 'Returns' line is redundant but harmless; nothing needed for correct invocation 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 100%, so the schema already documents file, scores keys, and the conditional problems requirement — the description largely repeats these ('scores 1-10 and worst problems'). The only added semantic is that the file must be the MD5-matched final artifact, which is a modest increment over the schema.

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 ('Log one self-review round') with explicit scope ('for a final preview file') and names the key inputs. It is clearly distinguishable from the sibling preview_review_sheets, which it references as the preceding step.

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?

Explicitly gives the sequencing trigger ('after preview_review_sheets') and the hard acceptance condition ('Every score must reach 8+ on the exact final file (MD5-matched) or preview_upload and the gate refuse'), including what happens on failure. Alternatives and consequences are both named.

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