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

Annotations already declare the non-read-only, non-destructive, closed-world profile, so the safety bar is lower. The description still adds real behavior beyond that: props are merged rather than replaced, and setting component to null restricts the overlay to custom code. It omits what happens to fields not supplied (are html/css/js replaced wholesale?) and any permission or validation requirements.

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?

A single dense sentence with the mutable surfaces front-loaded and zero filler. It is slightly telegraphic ('or its html/css/js'), which costs a bit of readability but not correctness.

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 an 8-parameter mutation tool with a nested props object and no output schema, the description covers the core edit semantics but leaves the required clipId and name unaddressed and does not state the effect on omitted fields. Adequate to call correctly in the common case, incomplete for edge cases.

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 13% (just projectId), so the description has to carry weight and it partially does: it explains the merge semantics of props and the null meaning of component, which the schema does not. However the required clipId and the name parameter are never mentioned, leaving three of eight parameters unexplained in both places.

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 uses a specific verb ('Change') with a specific resource ('an overlay') and enumerates the mutable surfaces (props, component, html/css/js). It is clearly distinct from add_html_overlay in intent, though it never names a sibling to route against.

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?

There is no when-to-use guidance: nothing says when to edit an existing overlay versus adding a new one, nor when to prefer update_clip or update_effect. The only conditional information ('component (null = custom code only)') is a parameter rule rather than usage routing.

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