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

Annotations already declare readOnlyHint=true, so the description's job is to add context, and it does: a hard cap of the last 1000 invoices, the fields returned, and the underlying GET /racun endpoint. It stops short of stating ordering or what happens at the page boundary, but the safety profile is fully covered by annotations.

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 short sentences, front-loaded with the resource and the 1000-document cap, followed by the sibling pointer and endpoint. 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 compensates by naming every returned field, and it covers the retrieval limit, pagination implication, and the detail-lookup alternative. 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 coverage is 100% and the single `page` parameter already documents the >1000-document case. The description's 'last 1000 invoices' framing corroborates but does not add syntax or semantics beyond what the schema states.

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 (list invoices of the Solo account) and enumerates the exact fields returned: id, number, date, gross total, status, status colour. It also distinguishes itself from the sibling read tool by scoping itself to listing rather than detail retrieval.

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 detail lookups to solo_get_invoice 'with an id', giving the agent a clear alternative. It does not spell out the inverse condition (when not to list), but the list-vs-detail split is unambiguous in practice.

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