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

The description thoroughly discloses merge semantics: only included keys change, nested values replace whole keys, null removes keys, the id can target elements anywhere in the tree (including nested in groups or masks), and the result is re-validated. This goes well beyond the annotations (which only say readOnlyHint=false, destructiveHint=false) and gives the agent essential behavioral expectations.

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 concise yet information-dense: four sentences cover the core mechanism, scope, nested-value behavior, null handling, alternative tools, and validation. Every sentence adds critical context with no redundancy or filler.

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?

Given the tool's complexity (merge patch, nested objects, arbitrary tree locations) and the existence of an output schema, the description is complete. It covers what the tool does, how patching works, edge cases (null removal, nested replacement), and safety (re-validation). No gaps remain for the agent to misinterpret.

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 already covers all parameters with descriptions (100% coverage), so the baseline is 3. The description adds value by explaining the 'patch' semantics with an example (keyframe_animations) and clarifying that id can reference nested elements anywhere in the tree, which is not in the schema. This nuanced guidance justifies a score above baseline.

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 opens with a specific action: 'Change fields on the element with the given id by merging in a partial element'. It clearly identifies the resource (element) and mechanism (merge). It also distinguishes from siblings by explicitly framing it as 'TWEAKING an existing composition' and contrasting with set_project.

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 usage guidance: 'This is for TWEAKING an existing composition. To create a composition or change many elements at once, edit the JSON and call set_project instead.' This tells the agent when to use this tool and what to use instead, effectively differentiating it from add_element and set_project.

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