get_inbound_pages

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

Goes well beyond the readOnly/idempotent annotations: signed_urls behavior on live vs. sandbox keys, the fact that agents are never issued image URLs, the structured-policy check, and the explicit 'Stop on denial; never switch keys or mail APIs to bypass it' instruction. It also flags that returned text is untrusted data, never instructions — security-relevant behavioral context an agent genuinely needs.

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?

Front-loaded correctly with the action and endpoint, but the paragraph is dense and drifts into policy text about proposals, forward destinations and discard checks that pertain to handling tools rather than a page reader. That content dilutes the read-specific guidance and costs structure points.

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?

For a read tool with full annotations and an output schema, the definition still names the returned fields (ocr_status, text/needs_review, is_blank, uncertain_spans) and covers auth, environment and pagination context. Nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so all five parameters (kind, limit, offset, item_id, signed_urls) are already documented in the schema, including the kind enum and the ONE-hour-URL semantics. The description mostly restates this (signed_urls, kind meanings) rather than adding syntax or edge cases beyond the schema, so the 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?

States a specific verb and resource ('Read an item's scanned pages') and pins it to the exact endpoint GET /v1/inbound-items/:id/pages, then distinguishes the page kinds (exterior envelope vs. interior after Open & scan). An agent immediately knows this is the page-content reader and what it returns, without needing to open the schema.

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?

Gives real usage conditions: key scope (inbound.item.read, agent.inbox.read), the member-vs-agent key visibility rules, and the environment binding. It never names a sibling as an alternative or states when not to use it, so it falls short of the 5-level 'when/when-not/alternatives' standard.

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