get_suprsend_object_preferences

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

The description says 'Read', indicating a read-only operation, but the annotations include destructiveHint: true, contradicting the description. Per the rubric, a contradiction between description and annotations results in a score of 1. The description itself is transparent about reading preferences, but the mismatch with annotations undermines trust.

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 at about 6 sentences, organized into a clear statement of purpose, when to use/not use, and return behavior. Every sentence adds meaningful information without redundancy.

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 presence of readOnlyHint and idempotentHint annotations, and the description covering purpose, usage, and parameter semantics, it is largely complete. The only minor gap is the conflicting destructiveHint, but that is an annotation issue, not a description completeness issue. It could mention that no changes are made, but the readOnlyHint already covers that.

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 coverage is 100%, so baseline is 3. The description adds value by explaining how to use optional parameters: 'Pass category to scope to one preference; omit for the full tree. Set channel_preferences=true to include per-channel overrides.' This goes beyond the schema's basic descriptions.

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 tool reads an object's category-level notification preferences and optionally per-channel overrides. It uses a specific verb ('Read') and resource ('object's category-level notification preferences'), effectively distinguishing it from sibling tools like get_suprsend_object (identity/channels) and get_suprsend_user_preferences (user preferences).

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?

Explicit when-to-use scenarios are provided: before update_suprsend_category_preference_object and before sending to an object to check delivery permission. When-not-to-use is also clearly stated, naming alternative tools for other cases (get_suprsend_object for identity/channels, get_suprsend_user_preferences for users).

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