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

Beyond the annotations (readOnlyHint=false, openWorldHint=true), it discloses that the call mutates the books, that the resulting booking cannot be deleted through the API, that each call is confirmed by default (with an opt-out), and that it reaches other people and needs a scoped API key. That is substantial behavioral context not derivable from structured fields; destructiveHint=false is not contradicted since the operation creates rather than destroys data.

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 and the type taxonomy are front-loaded, and every sentence carries operational information. It is on the long side, with confirmation guidance split across two sentences (default confirmation plus "confirm with the user before each call"), which is mildly redundant.

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 9-parameter, no-output-schema mutation tool, the description covers purpose, required inputs, type semantics, irreversibility, and auth. It doesn't describe VAT handling (in_ex_vat) or relation/cost-center usage beyond the schema, leaving a small gap for the non-type parameters.

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%, but the schema's own type description ("1 to 7, see details") is uninformative, and the description supplies the actual mapping for types 1–7 plus the row composition (amount, invoice_number for types 3/4). It adds real meaning over the schema, though it omits rows from its stated required list even though the schema marks it required.

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?

The description gives a specific verb+resource ("Book a mutation") and then enumerates the concrete booking kinds it covers (payment, money in/out, general journal entry), which distinguishes it from siblings such as e-boekhouden_create_invoice or list_mutations. An agent can tell exactly which tool performs a ledger booking without opening the schema.

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?

It states clear operational context: required fields, the meaning of each type value, and the precondition that the user's Cotlet API key must have access to this app. It also mandates user confirmation before each call. It does not explicitly contrast itself with sibling write tools (e.g., create_invoice), so it stops short of a 5.

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