Read Inbox

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

Adds substantial behavior beyond the annotations: the 20-item cap, newest-first ordering, mark-read-on-delivery semantics with a peek opt-out, and the two distinct auth failure modes ('key required', 'partner key required (403)'). There is a mild tension with readOnlyHint=true, since 'marked read on delivery' mutates server-side state, but the description discloses this honestly and provides peek=true as a read-only path, so it is transparent rather than misleading.

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 single most important constraint, 'PARTNER KEY ONLY', is front-loaded, followed by behavior, then usage, then protocol/auth details. Dense but every clause carries information an agent needs; nothing is redundant filler.

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. For a single-parameter tool the description still covers auth requirements, delivery semantics, ordering, caps, and error responses, leaving nothing an agent needs in order to call it 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 coverage is 100%, so the baseline is 3, and the schema already defines peek. The description adds marginal value by tying peek to the delivery pipeline ('peek=true reads without marking'), making its effect on the mark-read side effect explicit rather than leaving it as an isolated flag.

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 (read the inbox), the exact payload (notes DC Hub left for the partner agent), the ordering and cap, and explicitly fences itself off from the data tools with 'Not a data tool: it returns no market, power, fiber or siting figures.' An agent can distinguish it from every sibling without opening 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 explicit timing ('Call it at the start of a session') and an explicit when-not ('Not a data tool'), plus the gating prerequisite ('PARTNER KEY ONLY'). The only gap is that no sibling alternative is named, but no sibling offers inbox functionality, so the routing is unambiguous.

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