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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds one genuinely useful behavioral fact beyond them: the query is free and does not consume tokens ('Sin costo'). It does not describe what the response contains (token count, expiration, etc.).

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?

Two short fragments with no filler, and the resource is front-loaded. It is slightly clipped for a purpose clause, but nothing is wasted.

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 trivial zero-parameter read tool this is nearly sufficient, but with no output schema the description is the only place a return-value description could live, and it never says what checking the balance actually yields.

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?

The tool takes zero parameters, which is the baseline-4 case. No parameter explanation is required, and the description correctly avoids inventing any.

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 the concrete resource (available tokens in the account) and its scope ('Extraer Datos de INE'), which is clearly distinct from the extraction sibling extraer_ine. The verb is implied rather than stated, but an agent can tell what it returns.

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?

There is no explicit when-to-use guidance or routing toward alternatives. 'Sin costo' implies the call is free and therefore safe to check before consuming resources, but this must be inferred rather than being stated as a condition.

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?

Far exceeds the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), which only flag that this is a non-idempotent write. The description discloses the 15-minute open window, the 15-minute capture window, that data bypasses the conversation and goes to the configured destination, the cost model (free to create, 1 token per capture, refunded on failure), and the 20-live-link cap.

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 is front-loaded, and each following sentence carries a distinct operational fact (expiry, routing, cost, quota, return values). No sentence restates another or wastes space despite the density.

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?

With no output schema, the description correctly supplies the return fields (url, expiresAt) and warns the url is shareable only with the client. Combined with limits, cost, and delivery routing, an agent has everything needed to invoke and interpret this 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 coverage is already 100%, so baseline is 3, but the description adds real meaning beyond the schema by explaining what destination_id actually does (routes to webhook, email, or Telegram configured in the panel) and noting the returned url/expiresAt. It does not add format detail for reference or require_back, but the schema covers those adequately.

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 (creates a one-time capture link) and immediately explains the mechanism: a client photographs their INE/passport from their phone. This is clearly distinguishable from the siblings extraer_ine (which performs extraction) and consultar_saldo (which checks balance), since this tool only mints the link.

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?

Implies the use case well: the client captures remotely and the data is routed to destination_id rather than into the conversation, which tells an agent when this is the right tool. However, it never explicitly contrasts itself with extraer_ine or states when NOT to use it, so it stops short of full routing guidance.

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, openWorldHint=true, idempotentHint=false. The description adds important non-schema behavior: it consumes 1 token, refunds on LOW_IMAGE_QUALITY or extraction failure, and keeps personal data in the conversation. It does not cover auth or idempotency, but the added cost/refund/privacy context is strong.

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?

A single dense paragraph that front-loads what is extracted, then input details, cost/refund, and privacy. Every sentence carries necessary information; 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?

For a 2-parameter extraction tool with no output schema, the description is nearly complete: it lists return fields, input formats, cost, refund policy, and data handling. It could be slightly richer about output structure (e.g., JSON shape) or error modes, but is adequate for correct invocation.

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% and already documents both parameters, but the description adds accepted image formats (JPEG, PNG, WebP), a 10 MB size cap, and clarifies back_path is optional—meaningful constraints beyond the schema text.

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 ('Extrae los datos de una credencial para votar INE/IFE') and enumerates the extracted fields, making it unmistakable versus siblings like consultar_saldo or crear_enlace_captura.

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?

Provides clear context (photos stored on this computer, optional back_path) and operational constraints (file types, size limit), but does not explicitly state when not to use it or name alternatives—though none of the siblings overlap.

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