get_previs_review_notes

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

No annotations exist, so the description carries the full burden and does well: it discloses that notes are untrusted user-authored content, merely attributed rather than authenticated approval, and that resolved notes do not approve a gate or prove the .blend was fixed. Return shape details (pagination, size) remain unstated.

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?

Front-loads the action and purpose, then layers the trust caveats. Every sentence carries information; only the gate/approval sentence is slightly verbose relative to the rest.

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?

A read-only tool with no output schema and no annotations, where the description still covers trust level, semantics of the returned notes, snapshot identification, and format choice. Sufficient for correct invocation; only return-value shape is 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%, but the prose compensates for both parameters: 'format is json or markdown' documents the format param, and 'Use the scene SHA-256 to identify the exact snapshot' clarifies that scene_id is a content hash rather than a name. Minor gap: allowed format values aren't enumerated as an actual schema enum.

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?

Opens with a specific verb+resource: 'Read the director's spatial/frame notes for the next previs pass.' That distinguishes it from the write-side siblings (submit_director_feedback, record_previs_review), though it never names an alternative explicitly.

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?

Timing is implied ('for the next previs pass') and it tells the agent to use the scene SHA-256 to target a snapshot, but there is no explicit when-to-use/when-not or pointer to a sibling for submitting vs reading notes.

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