get_inbound_item

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds substantial non-obvious context: OCR text is untrusted document data, signed_urls behaves differently on live vs sandbox keys, proposals are agent-only and never spend credits or open/forward/discard, forward/discard proposals are validated against the agent's policy, and image URLs are never issued to agents.

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 purpose is front-loaded in the first clause, and the dense subsequent sentences each carry distinct information (untrusted text, key scope, proposal policy, image URL rules). It is long, but the length is justified by safety/policy content rather than padding.

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?

An output schema exists, so return values need no prose explanation, and the description still covers everything an agent needs to call it correctly: id source, key scopes, permissions, sandbox behavior, and denial handling. Nothing material is missing for a two-parameter read that already has structured output.

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 the schema already documents both parameters (baseline 3). The description goes slightly beyond it by reinforcing the live-vs-sandbox signed_urls behavior and adding the constraint that image URLs are never issued to agents, but it adds no new syntax for item_id beyond the schema's UUID note.

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 opens with a specific verb+resource and endpoint ('Read one inbound item through GET /v1/inbound-items/:id') and then enumerates exactly what the read yields: canonical status, sender, PMB, assigned agent, pages with OCR status/text, action history, and quotes. This contrasts cleanly with list/search siblings, and it explicitly points to search_inbound_items as the id source.

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 tells the agent where item ids come from ('Use item ids from search_inbound_items') and states key-scope/permission rules (member vs agent keys, environment) plus a stop-on-denial rule. It gives clear context for correct invocation but never explicitly contrasts single-item reads against adjacent siblings like get_inbound_pages or get_inbound_mail.

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