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

Annotations already declare readOnly/idempotent/non-destructive, but the description goes further: it explains exactly what is returned (all-in EUR price for both options plus inclusions), warns that Notificados is a tercero de confianza and NOT a Correos burofax, and mandates passing that distinction on. That is meaningful behavioral context an agent cannot get from the 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?

Front-loaded with the trigger and the return value, and every sentence carries information. It is dense and would read better with the two options bulleted separately, but there is 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?

No output schema exists, so the description must describe results — and it does, specifying both prices, currency, and what each option includes, plus the default behavior when no length is supplied. An agent has everything needed to call it and relay the answer 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%, so the fields are already documented; the description still adds the precedence rule — use pages if known, else text_length for an estimate, and with neither it quotes one page. That default/lookup logic is genuinely beyond the schema, though the individual parameter meanings are mostly restated.

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 ('quote ... burofax') and immediately scopes it to cost comparison for sending to Spain. It clearly separates itself from create_burofax_draft and the other siblings by framing itself as a pricing-only tool.

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?

Gives concrete triggers ('asks how much it costs', 'wants to compare delivery options before writing it') and an explicit exclusion with a named alternative: 'Do not use it to create the letter; use create_burofax_draft'. It also states 'Does not send or reserve anything', removing ambiguity about side effects.

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