Ver a referência

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

With no annotations, the description carries the full load and does well: it discloses that files are downloaded, that frames extraction requires ffmpeg (an external dependency), that nothing is persisted by default, and that save=true writes to ~/godly-media/<id>. It omits what happens when ffmpeg is absent or how large responses/images are handled.

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, front-loaded with the core action, then the motion variant, then the persistence rule. Every clause conveys a distinct operational fact, though the mix of Portuguese prose with English keywords is slightly dense.

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 5-parameter tool with no annotations and no output schema, the description covers the mechanic, side effects, and external dependency well. The remaining gap is failure behavior (missing ffmpeg, items with no media), which is minor but would matter for an agent.

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 3 is the baseline, but the description adds real meaning: frames > 0 implies downloading the video and sampling N spread-out frames with ffmpeg, and save=true implies writing stills/videos/frames to ~/godly-media/<id>. This goes beyond the schema's terse field descriptions.

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 and resource: downloads the still (video poster or image) for each media of an item and returns it as an image, plus a frames mode for video. An agent can tell this is a visual-reference fetcher, distinct from godly_get's data retrieval, though the description never names the sibling it replaces.

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?

Gives a clear conditional rule for the frames mode ('Pra motion, peça frames > 0') and implies the default still-only path, but says nothing about when to choose this tool over godly_get or godly_browse, nor what to do when an item has no media.

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