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

Annotations indicate readOnlyHint=false, consistent with the description's mutating action. The description adds that it returns the project identity with its result and that only passed fields change, which is useful behavioral context. It does not disclose potential side effects beyond that, but given the annotations are minimal, the description carries the burden well.

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 two sentences, front-loaded with the critical project-scoping constraint and then the action. Every sentence serves a purpose: scope, action, partial-update behavior, and id sourcing. No wasted words.

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?

The tool has 6 parameters and no output schema, so the description must compensate. It covers the action, scope, and id source, but does not elaborate on the semantics of x, y, scale, and start (e.g., coordinate system, units, whether start is in seconds or frames). For a moderately complex tool, this is a gap, but the description provides enough to get started.

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% (only project_id has a description). The description mentions 'reposition/retime/resize' which loosely maps to x, y, scale, start, but does not explain units, array types for x/y, or what start means. It does clarify the source of id, which adds value, but it does not fully compensate for the low schema coverage.

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 clearly states the action: reposition/retime/resize an EXISTING overlay, with concrete examples ('move the logo to the other corner', 'make the PIP smaller'). It distinguishes from add_overlay by emphasizing 'EXISTING' and 'only the fields you pass change', making it unambiguous what this tool does versus its siblings.

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 provides context that this is for modifying an existing overlay, not creating one, and specifies that id should come from get_edl. However, it does not explicitly mention when to avoid this tool (e.g., when adding a new overlay) or compare to set_overlay_motion, which might be a similar sibling. The guidance is clear but not exhaustive.

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