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

Annotations already indicate mutation (readOnlyHint=false), idempotency, and non-destructive nature. The description adds key behavioral context: keyframe t=0 is overlay-own start (not program time), scalar means static, and it returns the project identity with the result. It also notes scope is project-scoped and not inferred from active pointer. No contradictions with annotations.

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?

The description is dense but well-structured, front-loading the project-scope and core action. Each sentence contributes (scope, what it does, keyframe timing, scalar meaning, exclusions). It is longer than necessary but not verbose, and the information density justifies the length.

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 tool with a nested motion object and no output schema, the description explains the motion structure thoroughly, including units, keyframe format, and edge cases (full-frame B-roll, screen takeovers). It also indicates the return value (project identity with result) and how to obtain the project_id. Minor omission: no explicit mention of error conditions or pagination, but these are not critical for this call.

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?

The schema covers 75% of parameters (id lacks description). The description adds crucial semantic details for the motion object: x/y/scale are frame fractions, rotation in degrees, opacity 0..1, and keyframe t is seconds from overlay start. It also clarifies that a scalar makes a property static, adding meaning beyond the schema.

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 states a specific verb ('Author or replace') on an EXISTING visual overlay for x/y/scale/rotation/opacity, and distinguishes it as the general motion-graphics primitive versus stacking named presets. It also clearly scopes the call to a specific project_id, making it unambiguous.

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?

It explicitly states when to use it (general motion for logos, images, PIP clips) and when not (full-frame B-roll covers ignore x/y/scale; screen takeovers reject ordinary curves). However, it does not name alternative tools explicitly, only implies them via exclusions.

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