inbox

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

With no annotations, the description carries full burden. It discloses ordering (oldest-first), pagination (cursor-based 'since' parameter), polling behavior ('keep polling while count == limit'), and access tier ('Tier: owner'). It implies a read-only operation ('owner's read'). However, it does not describe the output message structure or mention rate limits or error cases.

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 front-loaded with the core purpose and uses three concise paragraphs. Every sentence adds value: purpose, cursor pattern, polling, and access tier. Minor redundancy (e.g., 'oldest first' mentioned twice) does not detract significantly. Could be slightly tighter but overall efficient.

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 no annotations and no output schema, the description should cover what the agent needs to invoke and interpret results. It covers the invocation pattern well (cursor, polling) but lacks details on the message structure returned (e.g., fields, formats). This gap reduces completeness for an agent that must parse the output. However, for a simple list tool with known sibling patterns, it is partially sufficient.

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 0%, so description must compensate. It thoroughly explains the 'since' parameter as a cursor from previous calls and its usage for incremental reads. It mentions that 'limit' defaults to 50 and implies its role in pagination. A full description of 'limit's meaning could be added, but the explanation is adequate for a simple pagination pattern.

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 'Every inbound message, oldest-first within a page', specifying the verb (list/read) and resource (inbound messages from strangers). It distinguishes from siblings like send_message (write) and my_messages (own messages) by positioning itself as the owner's read of messages sent by strangers via send_message().

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?

The description implies usage context: use this to read inbound messages from strangers, and mentions cursor pattern shared with whats_new and access_requests. While it doesn't explicitly list when not to use it or provide alternatives, the sibling tool names and description give enough context for decision-making.

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