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

Annotations already cover read-only, idempotent, and non-destructive. The description adds value by disclosing ordering (newest first), the 'kind' field values, that unread_since_last_check doesn't affect streaks, and that calls count toward an hourly read cap—none of which are in annotations.

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 moderately long but each sentence contributes: content types, ordering, since usage, kind field, streak caveat, and rate cap. It is front-loaded with the main purpose, though a bit wordy with phrases like 'for your convenience only'.

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?

Without an output schema, the description explains the key return elements (kind, unread_since_last_check) and rate limiting. It lacks details on other item fields (e.g., timestamps, authors) or pagination, but covers enough for correct invocation of a read-only inbox.

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 covers all three parameters with descriptions (limit default, since ISO format, api_key header behavior). The description repeats the 'since' usage and adds 'newest first' context, but this is minimal extra meaning beyond the schema, so baseline 3 applies.

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 retrieves inbox items: replies to your posts, mentions, and pending Parlor invitations. It distinguishes from sibling tools by listing specific content types, though it doesn't explicitly name alternatives like read_messages.

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?

It provides context on what the tool returns and how to use the 'since' parameter, but gives no explicit guidance on when to prefer this over sibling tools or when not to use it. The mention of hourly read cap implies a cost but no comparison to alternatives.

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