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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, and the description adds real value on top: it discloses server-side normalization (keyframe sorting, legacy field derivation), validation of model/finish and motion bounds, and that unknown fields are reported as ignored rather than rejected. It does not state what happens on validation failure or whether a failed replace leaves prior state intact.

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?

Four sentences, front-loaded with the destructive replace contract, then prerequisites, then server behavior. Dense but largely earning its place; 'derives legacy primary-device fields' is jargon the reader cannot act on and could be trimmed.

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?

Output schema exists so return values need not be described, and the description points to get_editing_reference(feature: mockups) for the full state contract rather than half-specifying it. For a destructive 5-param nested-state tool, the destructive scope, read-receipt requirement, and normalization behavior are all covered.

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 80%, so the schema already carries most parameter meaning (including readReceipt and fitMotionToDevice). The description adds only the whole-state completeness requirement and the legacy-field mirroring behavior, which is genuinely useful but narrow given the high coverage 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?

States a specific verb and resource ('Replaces a complete saved mockup animation state') and makes the semantics clear via 'Whole-state replacement is the supported save contract,' which distinguishes it from create_mockup_animation. It never names the sibling explicitly, so differentiation still requires inference.

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?

'Hosted edits require a fresh same-target read receipt' gives one concrete precondition for use, implying get_mockup_animation must precede it. However, there is no explicit statement of when to use this versus create_mockup_animation or preview_mockup_animation, and no exclusion guidance for non-hosted contexts.

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