Remite

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

Beyond the annotations, the description discloses that the check is offline, exactly what it validates (required fields, postcode range, province consistency), what it returns (normalised fields plus problem messages), and a key limitation (does not confirm street or person existence). This is rich behavioral context that an agent would otherwise have to discover.

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 description is front-loaded with when to use, then moves through what is checked, what is returned, and the key exclusions. Every sentence adds value with no wasted words.

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, but the description explains the return shape (normalised fields + problem list). It covers validation rules, limitations, and exclusions, so an agent has everything needed to call it correctly without guessing.

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 baseline is 3. The description adds meaning by clarifying which fields are required for delivery, the postcode range (01000–52999), and the province–postcode matching rule—details not present in the schema.

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 states a specific verb (check) and resource (Spanish postal address), and explicitly situates it before creating a burofax. An agent can tell exactly what this tool does and how it fits with the sibling create_burofax_draft.

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 gives clear when-to-use (user provides a Spanish address, before creating a burofax) and an explicit exclusion (do not use for addresses outside Spain). It does not name the alternative sibling (create_burofax_draft) by name, but the workflow context is strong enough to route correctly.

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

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

Annotations already declare readOnlyHint=false and destructiveHint=false, and the description adds the crucial nuance: nothing is sent and nothing is charged, the draft is only actionable after payment on review_url. It also discloses content rules (no legal claims added, never include DNI/NIE/NIF) and the output fields. It does not mention rate limits or what happens to an existing draft with the same content, so it falls just short of the top mark.

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 description is front-loaded with the trigger condition and approval workflow before the output behavior and exclusions. It is dense but nearly every clause carries operational meaning; the only slight excess is the repetition of the no-payment/no-send message alongside the post-call instruction.

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 non-readonly, nested-object, six-parameter tool with no output schema, the description covers inputs, side-effect limits, the return payload (page count, prices, review_url), and the required follow-up conversation. Nothing an agent needs in order to call it correctly or explain the result is missing.

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 100%, so the baseline is 3. The description goes beyond it by explaining that the body must be passed exactly as approved with no address blocks, date or signature (those are added automatically), and by warning against ID numbers, which is a real semantic constraint not encoded in the schema.

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 states a specific verb and resource ('renders the exact A4 letter ... as a PDF, stores it as a draft') and names what it returns (page count, per-option price, review_url). It also explicitly names the siblings it is not for ('use quote_burofax' for prices, 'get_burofax_status' for tracking).

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 gives explicit preconditions (user has approved the final text and supplied both postal addresses in Spain), the required pre-call step (show the full text and get approval), and the post-call step (show review_url, tell the user nothing goes out until they pay). It also routes to the right sibling for prices and tracking.

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

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

The annotations already declare read-only, idempotent, non-destructive behavior, and the description adds useful context about what is returned: current status, a dated timeline, and a status page link. It could mention authentication, rate limits, or error behavior, but those are less critical for a read-only status lookup.

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 description is front-loaded with the usage condition, then explains the accepted input, return value, and safety boundary. Every sentence contributes useful information, and the read-only note is compact enough not to feel 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 one-parameter read-only status tool with no output schema, the description supplies the trigger conditions, input sources, expected return shape, and an explicit non-use case. Nothing critical is missing for an agent to select and invoke it 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 schema already documents the single reference parameter. The description adds meaningful detail beyond the schema by naming the concrete order-reference format, the source of each reference type, and the fact that a full review or status link is also accepted.

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 states a specific verb and resource, explaining that the tool answers whether a burofax was paid, sent, delivered, or has a certificate. It also clearly distinguishes itself from create_burofax_draft by saying it must not be used to create or change a letter.

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 explicitly names the triggering user questions and accepted reference sources, including the order reference from the receipt email or the draft reference returned by create_burofax_draft. It also gives a clear exclusion: do not use this to create or change a letter.

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

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.