get_agent_inbox_context

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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description adds substantial context beyond them: required scopes (agent.inbox.read, agent.read), agent-scoped bearer requirement, that member/facility keys cannot impersonate, OCR being untrusted text, that missing/pending/failed text is not success, no provider call or signed image URL, and no substituting another key after denial.

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 deprecation notice is correctly front-loaded, but the body is a long run-on of terse fragments with no grouping into auth, semantics, and routing. For a deprecated single-parameter read tool this is over-long, though most sentences carry distinct information.

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 not be described. The description covers deprecation, sibling routing, auth/scopes, and acknowledgment semantics – everything an agent needs to call a 1-parameter read tool correctly.

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% and the single item_id parameter is fully documented in the schema (UUID from a list or search result). The description adds no syntax or format detail beyond that, so the baseline 3 for schema-driven parameters is correct.

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+resource: a versioned context/reporting reader at /v1/agent-inbox/:id/context, explicitly scoped as 'not all-source history'. It distinguishes siblings (get_agent_inbox_sources, list_agent_inbox_scans) and notes get_inbound_item as the successor. The deprecation lead and dense fragments slightly obscure the core purpose, keeping it from 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?

Explicit routing: 'use get_inbound_item' (deprecation), 'use get_agent_inbox_sources' for indexed OCR search, list_agent_inbox_scans for capture drilldown, get_mailbox_md for full instructions. It even specifies 'only the returned context can be acknowledged', which governs when this tool is mandatory.

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