create_reimbursement

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

With no annotations, the description carries the full behavioral burden and does disclose the key trait: without confirm=true it only returns a preview (non-mutating), and acting_as must be confirmed via connect_tricount. It omits permissions, error behavior, and what the preview actually returns.

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 purpose and the preview/save rule are front-loaded in the first two sentences, followed by a readable Args block. The Args list is somewhat verbose but each line earns its place given 0% schema coverage; minor redundancy with field names.

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?

No output schema and no annotations, so the description must cover behavior and params, which it largely does, including the preview/commit distinction and all parameter meanings. It is slightly incomplete on return shape of the preview, error cases, and required permissions for a mutation-capable tool.

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 0%, so the description must compensate, and it does so for all eight parameters: acting_as is defined with pronoun mapping ("Yo", "me" refer to this member), from/to member roles are disambiguated (payer vs receiver), amount is constrained positive, date defaults to today, and confirm means real save. This is meaning well beyond the bare schema titles.

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?

"Registra un reembolso (transferencia) de un miembro a otro" states a specific verb (register) and resource (a reimbursement/transfer between two members), which an agent can distinguish from create_expense. It stops short of explicitly naming or contrasting itself with the sibling expense/transfer tools.

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?

"Sin confirm=true solo devuelve una vista previa" gives a clear conditional for the dry-run vs commit mode, which is real usage guidance. However, it never says when to prefer this over create_expense or delete_entry, nor any prerequisite beyond the acting_as note.

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