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

readOnlyHint already declares this a safe read, but the description adds behavior the annotations do not: the sort order (newest shipped first) and the fact that rows are bounded summaries rather than full records. It does not mention pagination behavior or default limit, which are minor gaps.

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?

Three tight sentences, front-loaded with the resource and ordering, then the mode switch, then the routing hint. The field enumeration is dense but earns its place since there is no output schema. Slightly long, but no 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?

With no output schema, the description carries the return-shape burden and does so by enumerating the summary fields (id, version, shipped date, counts, presentation flag). Combined with the active/archived switch and the get_delivery handoff, an agent has everything needed 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 description coverage is 100%, so all four parameters (limit, offset, archived, projectId) are already documented in structured data. The description reinforces archived rather than adding syntax or format detail, 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+resource (list a project's deliveries) with scope (per-project), ordering (newest shipped first), and the exact shape of what is returned. An agent can distinguish it from get_delivery or list_batches 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?

Explicitly routes between modes: lists active deliveries by default, archived=true for archived ones, and directs to get_delivery for rationale/summary/batches. Both the condition for a parameter and the alternative tool are named, leaving nothing to inference.

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