inbox_pull

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

With no annotations, the description carries the full burden and does disclose the key trait: at-least-once delivery with unacked pulls being redelivered, plus the fact that bodies are returned. It omits auth/trust-mode behavior and what happens on ack, but the redelivery contract is the critical disclosure and it is present.

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?

Three short clauses with no waste; the core semantics and the at-least-once caveat are front-loaded, and the docs pointer is a compact trailing reference instead of prose bloat.

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?

With 6 params covered at 100%, an output schema present, and the delivery guarantee stated, an agent has what it needs to call this correctly. Only the trust-mode/auth nuance and how the returned messages differ from inbox_peek output are left unstated.

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 limit, profile, lease_seconds, session_id, and session_secret are already fully documented in the schema. The description adds no parameter-level detail beyond implying the lease/renew flow, so the baseline of 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?

States a specific verb and resource ('take your unread messages into in-flight and return them WITH body') and adds a differentiating qualifier ('index-free; no cursor') that separates it from cursor-based readers like event_cursor. It does not name the closest sibling (inbox_peek), so it stops short of a 5.

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 the use case (consume unread mail as in-flight messages) and points to inbox_extend for mid-turn lease renewal, but never states when to prefer this over inbox_peek, inbox_history, or message_list. Usage is inferred rather than guided.

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