Auditoría Forense de Colusión, Vinculación y Procesos Viciados

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, destructiveHint=false), and the description usefully adds what the agent cannot infer: the four-step pipeline (bidder trace, RPE cross-check, red-flag detection, legal opinion) and the legal basis (Art. 14 Ley 340-06, Art. 65 Dec. 543-12). It stops short of disclosing scanning depth, latency, or what happens when the process has no bids.

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 purpose sentence, then a tight four-item numbered breakdown that maps to real behaviors rather than padding. Slightly long, but every numbered item carries distinct information about what is checked and what is produced.

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 burden and does so adequately: it names the deliverable (a dictamen legal with legal grounds for descalificación de oficio or impugnación) and the detection categories. It comes up short only on output structure and any caveats about coverage limits.

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% — both codigo_proceso and paginas are documented in the schema, including the default, min, and max for paginas. The description adds no parameter-level detail (no format guidance, no effect of raising paginas on recall), so the baseline 3 is appropriate.

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 (audita forensemente) and a narrowly scoped resource (las ofertas de un proceso, cruzadas contra el padrón RPE), then enumerates the exact red flags it looks for. This is clearly separable from siblings like dgcp_auditor_pliego_trampa (audits the tender document) or dgcp_radiografia_proveedor (single-provider profile) without opening any 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?

The description makes the use case evident ('detectar amarres o colusión' in a specific process), but never states when to prefer it over overlapping siblings such as dgcp_inteligencia_proceso, dgcp_auditor_pliego_trampa, or dgcp_generador_recurso_impugnacion. Usage is implied by scope rather than routed explicitly, and there are no exclusions or prerequisites (e.g. process must already have bids).

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