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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context through the worked example (auto-calculation of splits, payer also being a recipient), but says nothing about required permissions, whether the group must pre-exist, or balance side effects.

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?

Purpose sentence is front-loaded and the example, while long, is dense with non-redundant information for a 9-parameter nested payload. Slightly heavy for a two-sentence description, but every clause earns its place.

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?

For a create mutation with nested objects, no output schema, and partial schema coverage, the definition is workable but incomplete: it never states what the call returns, what validation failures look like, or the meaning of several required top-level fields. The example covers the split mechanics well but leaves other gaps.

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 only 56% across 9 params with nested objects, so the description must carry weight. The concrete example uniquely disambiguates the hardest part of the schema: how the participants cashFlow entries map to the splitConfig participantConfigs, and how isAutoCalculated interacts with the split modes. It does not cover groupId, currency, categoryId, description, or transactionDate.

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 (Create) and resource (shared expense, transfer or income in a group), immediately distinguishing it from create_personal_transaction and the update/delete/list group siblings via the word 'group'. It does not explicitly name an alternative, but the scope is unambiguous.

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?

The description explains the shape of a call via an example but gives no when-to-use guidance, no conditions, and no reference to alternatives such as create_personal_transaction or update_group_transaction. An agent gets no routing help beyond the tool name.

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