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

Adds substantial behavioral detail beyond the readOnlyHint and destructiveHint annotations: required features.manage permission even for read-only access, no read-marking side effect, inclusion and identification of spam/snoozed items, pagination drift warning, and an explicit prompt-injection caution for public text. This is exactly the kind of context an agent needs before invoking a read tool that touches untrusted content.

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 dense but front-loaded, moving from core purpose to filters, pagination, permissions, side effects, and safety in a logical order. Every sentence carries unique information, and there is no repetition 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 a read-only list tool with no output schema, five parameters, low schema coverage, and untrusted public content, the description covers permissions, pagination behavior, safety, and filtering well. It still leaves some parameter-level details (limit, account_id semantics) and return shape implicit, so it is strong but not exhaustive.

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?

With schema description coverage at 20%, the description must compensate for undocumented parameters. It clarifies state and query filtering ('filtered by state or literal text') and cursor following ('Follow next_cursor'), but does not explain limit, account_id beyond the schema's 'From list_accounts' note, or the cursor object structure. Partial compensation warrants a mid-range score.

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 ('Read active Feedback Inbox conversations') with ordering and optional filters, so the core operation is immediately clear. However, it does not explicitly distinguish itself from close siblings like list_inbox_messages or get_inbox_conversation, leaving some ambiguity about the conversation-vs-message scope.

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 clear operational context: active conversations, newest activity first, optional state or text filtering, and advises refreshing for a current overview because new activity can move items between pages. It does not name alternatives such as get_inbox_conversation for a single thread or list_inbox_messages, so guidance is strong but not fully routing.

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