BuildGets · Precios de obra y BC3

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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile needs no restating. The description adds genuinely new behavior: the returned fields, that warnings may be returned, and that the editor link expires after 24 hours — useful context beyond the structured fields.

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 sentences, front-loaded with what the tool returns before the invocation hint. The return-value enumeration is long but informative; no filler text.

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 carries the return contract and does so reasonably well (fields plus the ephemeral link). Annotations cover safety, so the only mild gap is error behavior for malformed BC3 input.

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 baseline is 3. The description goes slightly beyond the schema by framing 'contenido' and 'url' as the two alternative input modes (raw file text vs. public link), a relationship the per-property descriptions do not state.

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 ('Lee un presupuesto de obra en formato BC3 (FIEBDC-3)') and enumerates what it returns (título, PEM, capítulos, partidas, avisos). It is adequately distinct from the only sibling, precio_obra, though it never names or contrasts with it.

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 explains how to supply input ('Pasa el texto del archivo en "contenido" o un enlace público en "url"') but gives no explicit when-to-use condition, prerequisites, or exclusion versus precio_obra. Usage is implied rather than stated.

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 cover the safety profile (readOnly, non-destructive, closed-world), and the description adds substantive behavior beyond them: it discloses the return payload (precio típico, rango habitual, hasta 5 partidas with price, unit, código and ficha link), the data's currency (Base BuildGets 2026), and an important interpretation caveat ('precios de ejecución material, sin IVA'). This is real context an agent cannot get from structured fields.

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-loads the usage trigger first and then the value proposition, return shape and caveats — a sensible ordering. It is somewhat dense as a single long paragraph, and the 'mejor que una estimación general' claim is marketing-adjacent, but no sentence is pure 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?

With no output schema, the description carries the burden of explaining results and does so fully: typical price, usual range, up to 5 line items with their fields, VAT exclusion, and the request to cite the source link. Combined with annotations and full schema coverage, an agent has everything needed to call 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 description coverage is 100%, so the schema already documents both 'consulta' and 'unidad'. The description adds only indirect hints about the query content (the enumerated work types mirror what 'consulta' expects) but nothing about the optional unit parameter or format. Baseline 3 applies.

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 ('da precios reales de una base de precios actualizada — Base BuildGets 2026') and enumerates the work types covered (pintar, alicatar, ventanas, hormigón, impermeabilizar, demoler), which pins the scope tightly. It also contrasts itself against 'una estimación general', though it never differentiates from the only sibling, abrir_bc3.

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 a strong, explicit trigger: 'Úsala SIEMPRE que el usuario pregunte el precio o el coste de un trabajo de obra... aunque no mencione BuildGets', which is exactly the routing condition an agent needs. There are no when-not conditions or named alternatives, but the trigger is unambiguous for a single-purpose tool.

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