reels_import_pipeline

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

Annotations only declare it is not read-only, not destructive, and closed-world; the description adds genuinely non-derivable behavior: visuals materialize as explicit placeholders, the source tree is left untouched, and WGSL is not converted. That is exactly the kind of side-effect disclosure annotations cannot carry. It still omits whether the operation is idempotent or what happens if the project id collides.

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?

Two tight sentences, front-loaded with the action and target, followed by the constraint clause. No filler, no restatement of the tool name, and the negative scope is stated compactly in one clause.

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 two-parameter mutation tool with no output schema and thin annotations, the description covers side effects well but leaves the agent guessing about `projectId` semantics, the returned project identifier, and overwrite behavior. Adequate to attempt a call, not adequate to call confidently.

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 0%, so the description must compensate, and it only partially does: 'work/<slug>' implicitly explains that `directory` points at a work directory, with no format, path-resolution, or relative/absolute guidance. The `projectId` parameter — its optionality and whether omitting it auto-generates an id — is never addressed anywhere.

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 names a specific verb (Import) and concrete resources (narration, aligned words) plus the destination (a new editor project), and it scopes itself with 'existing work/<slug>'. What it does not do is name a sibling to contrast with (e.g., reels_import_asset vs. reels_create), so differentiation is left to inference from the phrasing.

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?

Usage is implied through the precondition 'an existing work/<slug> narration', which tells the agent the source must already exist, and the negative clause rules out an expectation of WGSL conversion or source modification. There is no explicit when-to-use versus reels_create or reels_import_asset, and no statement about what happens when the target project already exists.

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