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

Annotations cover the safety profile (idempotent, non-destructive, write), but the description adds what annotations cannot: the call is project-scoped and returns the project identity, and an explicit position/anchor_y 'removes any old shot-aware placement track' — a real side effect the agent would otherwise not anticipate. Error behavior on missing captions is also disclosed.

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 the project-scope constraint and the core purpose, and the arrow examples pack high intent-mapping value per token. However it is a single dense block, and the inline preset enumeration partially duplicates the schema enum, which slightly weakens scannability.

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 mutation tool with no output schema and a deeply nested style object, the description covers scope, return identity, side effects, applicability, and failure behavior — everything an agent needs to invoke it correctly without guessing.

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?

Despite 50% schema coverage on a 24-property nested style object, the description supplies meaning the schema lacks: size_scale's numeric interpretation (1.5 = 50% bigger), single_line's override of preset stacks, dynamic as legacy karaoke, and the roles of highlight_color, uppercase, emphasis_words, and position/anchor_y. The intent-to-parameter mapping examples ('make it red' -> color) directly enable correct invocation.

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 with explicit scope boundaries: 'Change how existing captions LOOK without touching their text or timing.' The contrast with add_captions (which creates captions and owns the preset menu) makes the distinction from siblings unambiguous even before opening the schema.

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?

Routes the agent explicitly: motion looks are documented in add_captions, and 'use this when the user says captions must stop moving' names the triggering condition for the position/anchor_y lock. It also states applicability ('works for from_transcript and manual captions') and the failure mode ('errors helpfully if no captions exist yet').

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