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

Annotations only declare the broad profile (not read-only, open-world, non-destructive); the description goes beyond them by disclosing the privacy scope ('only you can see: the person's asset list never shows it'), that the asset never enters the film, the shape of the answer (Asset ID, post length, caption), and the degraded path for unreadable platforms.

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-loaded with purpose and privacy scope, then usage, then the follow-up workflow, then return values, then an edge case and a cardinality rule. Dense and largely waste-free, though the single long paragraph carries enough distinct clauses that a reader has to work to separate the mutation constraints from the return description.

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?

There is no output schema, so the description must explain returns, and it does: Asset ID, length, caption, plus what happens for an unreadable platform. It also covers privacy, downstream tools, and per-call cardinality, leaving nothing an agent needs in order to invoke it correctly.

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 url, note and projectId are already documented, and the description adds little per-parameter detail beyond the 'one link per call' cardinality constraint and the hint about what the note should capture. Baseline 3 is appropriate when the schema carries the parameter semantics.

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 action (bring a public video post into the project) and a precise resource with a scoping qualifier: the asset is private to the agent, absent from the person's asset list, and never used in the film. That distinguishes it cleanly from import_asset_url, import_stock, import_gif and add_from_library, which all bring in usable material.

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 both trigger conditions ('when the person sends a link to a reel or short video they want theirs to feel like, or when you asked them for one') and the explicit follow-up route: watch it with read_asset, read_transcript, search_footage or inspect_media. It also states a hard usage constraint, 'One link per call,' and warns to take devices, not footage.

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