evaluar-encaje

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

With no annotations, the description does real work: it discloses the full rule set evaluated, the conditional salary check, and the categorical output including motivos. What it omits is the operational side — whether it is read-only, what happens if no master profile exists (error vs partial evaluation), and whether the evaluation is deterministic. Those gaps matter for a no-annotation tool.

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 tight sentences: the criteria enumeration is front-loaded and the return contract closes it. Every listed criterion earns its place because it tells the agent what the verdict will be based on, though the run-on enumeration is dense rather than scannable.

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, and the description compensates by naming the three verdict values and mentioning motivos, which is what the agent needs to interpret the result. For a one-parameter tool this is nearly complete; the missing prerequisite (an existing master profile) is the one real hole.

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 the single 'oferta' parameter already documents that it accepts a numeric id or a workatastartup.com job URL. The description adds nothing about that parameter. Baseline 3 applies when the schema carries the full burden.

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 (compara la oferta con el perfil maestro) and enumerates the exact criteria checked — modalidad, país, visa, tipo de empleo, experiencia, salario, tecnologías, inglés — plus the three possible verdicts. It is clearly distinct in substance from detalle-de-oferta (raw offer data) and comparar-perfil, though it never names a sibling to route against.

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?

Usage is only implied: an agent can infer this is the pre-application screening step, and the description does flag one conditional rule (salary is only checked if preferencias.salario_minimo_usd_anual is declared). But there is no explicit 'use when' / 'use instead of', and no statement that a master profile must already exist (construir-perfil-maestro / guardar-perfil-maestro are siblings that would matter).

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