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

Goes well beyond the annotations by disclosing deprecation/retirement timing, that the fixture is isolated, provider-free and involves no real mail, model call, email, facility task, PMB or charge, plus the auth model (agent-scoped bearer required). It also explains idempotent replay semantics and behavior shared with REST. This is rich behavioral context the structured fields do not carry.

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?

Deprecation and endpoint are front-loaded, and nearly every clause carries actionable information. It is dense and slightly repetitive ('Sandbox agent key only' vs 'Agent-scoped bearer key required'), which costs a point but does not obscure the core intent.

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; annotations cover the safety profile. Combined with the description's coverage of deprecation, auth, scope, idempotency and isolation, an agent has everything needed to call this 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%, so the schema already documents both parameters, including the enum and idempotency replay rule. The description largely restates the enum values and the same-key-same-scenario reuse behavior rather than adding syntax or format detail. Baseline 3 applies when the schema does the heavy lifting.

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 ('seed'), resource ('fixture'), the exact fixtures named (two_page_letter or needs_review), and the endpoint path (/v1/agent-inbox/sandbox/seed). It also front-loads the deprecation status, which no sibling exposes. An agent can distinguish this from read/report siblings like get_agent_inbox_scan without opening either 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 clear when-to-use constraints: sandbox agent key only, required scope agent.inbox.read, and member/facility keys cannot be substituted. It also rules out post-denial workarounds ('never substitute another key or mail API'). It does not name an alternative tool for seeding, but it explicitly states there is no successor, which closes that loop honestly.

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