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

Annotations already declare readOnlyHint=true, so safety is covered; the description adds genuinely new behavior by disclosing the pagination envelope and warning that a call returns one page only, not the whole portfolio. That is exactly the operational detail an agent needs before paging, and it does not contradict the read-only annotation.

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 compact clauses with the core scope and the read-only guarantee front-loaded. Dense semicolon chaining is efficient but slightly harder to scan than separate sentences; no filler present.

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?

It covers the return shape (data + vendor pagination) and the one-page constraint, which is valuable given there is no output schema. However, for an 11-parameter tool with several opaque enum/string filters and no per-parameter descriptions, the description leaves too much about filtering semantics unaddressed.

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 73%, which warrants the baseline 3. The description only gestures at the status and date filters ("payment status and dates") and says nothing about the undocumented or opaque parameters such as statement, transaction_type, or the date_from vs transaction_date_from distinction.

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?

Specific verb+resource: "Read financial transactions and rent charges, with payment status and dates", plus the endpoint. It is clear this is a list/read tool, though it never explicitly contrasts with the sibling arthur_get_transaction (single record) so the boundary must be inferred from the name.

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?

Usage is only implied (read transactions) and the one explicit constraint, "never posts money", is a non-capability statement rather than routing guidance. It gives no direction on when to use this versus arthur_get_transaction for a single record or arthur_list_invoices for invoice-level data.

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