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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is the data-scope boundary: these records are invisible to the other tools, and the returned shape includes owner @handle, phase, ETA and open tracking requests. That is genuine behavioral context beyond the annotations; it just doesn't cover permission or visibility rules for the sharing connection itself.

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?

Two dense sentences with no waste: identity and field list first, then the crucial non-overlap caveat. Parentheticals are load-bearing rather than 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 five optional parameters and no output schema, the description correctly compensates by describing what a record contains and what filter changes. Pagination (limit/cursor) is left entirely to the schema, which is acceptable given full coverage, but a note on result ordering or cursor behavior would have closed the gap.

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 every parameter including the filter enum and company resolution against list_companies is already documented. The description's mention of 'filter=requests' maps to that enum but adds no syntax or format detail the schema lacks, so 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 ('Shipments other companies (network connections) shared with this company') and enumerates the returned fields (owner @handle, carrier, POL/POD, phase, ETA, tracking requests). It explicitly distinguishes itself from the sibling list_shipments by noting these are 'not the company's own shipments' and that 'the other tools do not see them.'

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?

Clear context for when to reach for this tool (network-shared shipments only) and it names the alternative indirectly by excluding the own-shipment tools. It also flags the filter=requests mode for open tracking requests. It stops short of an explicit 'use list_shipments instead when...' instruction, but the exclusion is stated strongly enough to route the agent.

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