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

Annotations cover idempotency and non-destructiveness, but the description adds significant behavioral details: 'Never upscales beyond the source's pixels', 'focus_track replaces the complete per-shot track', and 'Tracks survive trims and speed changes'. Also clarifies scoping with 'acts only on the explicit project_id'.

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 scope and purpose, then systematically covers parameters, usage, and behavioral caveats. Every sentence adds value; no redundancy or fluff. The structure is logical and easy to parse.

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?

Covers all parameters, usage guidance, preconditions (read get_edl first), alternative tool, and a hint about the return value ('returns the project identity with its result'). Even without an output schema, the description is sufficiently complete for correct invocation.

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 only 17%, but the description thoroughly explains ratio values, mode meanings, focus_x/focus_y as fractions with origin, focus_track structure and units (SOURCE seconds), and the 'replaces' semantics. This fully compensates for the schema's lack of detail.

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 ('Set') and resource ('output aspect ratio for every render'), and explicitly contrasts with auto_reframe, distinguishing it from a key sibling. The description makes the tool's purpose unmistakable.

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?

Provides explicit guidance on when to prefer auto_reframe ('PREFER auto_reframe') and instructs the agent to read get_edl(frame) first, changing only desired spans. This gives clear usage context and alternatives.

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