Ver qué hay en la página

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

Annotations only declare readOnlyHint=true and openWorldHint=true; the description adds real behavioral context beyond that, notably that it traverses iframes and that tables include headers, row counts and an example row rather than full contents. The per-frame listing behavior interacts with the max_items cap, which is meaningful for an agent predicting output size. It does not say what happens when the page is on an unexpected frame or how truncation is signaled, which keeps it below 5.

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 and followed by the usage cue, with no filler. The element enumeration in the first sentence is dense but each item earns its place by telling the agent what will be visible. Slightly long as a single clause chain, but readable.

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?

There is no output schema, so the description carries the burden of describing return content, and it does so thoroughly by listing the page elements surfaced and the iframe traversal. For a read-only inspection tool with two documented parameters, an agent has enough to call it and interpret the result. The only gap is that expected markdown/json output shapes are not sketched.

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% and both parameters (max_items with min/max/default, response_format with its enum) are fully documented in the schema, so the baseline of 3 applies. The description adds nothing about when to raise max_items or when to prefer json over markdown, even though the json mode is directly relevant to an agent that will parse the result programmatically.

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 ("Resume la página actual de Educa") and enumerates the extracted elements: títulos, tablas con cabeceras y nº de filas, desplegables, filtros con opciones, enlaces, botones y mensajes, además de iframes. That is far more than a restatement of the name. It stops short of 5 because it never distinguishes itself explicitly from data-dumping siblings like educa_dump_html or educa_screenshot, so an agent must infer that this returns a condensed summary rather than raw markup or an image.

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 when-to-use guidance with named alternatives: orient yourself before educa_click or educa_select_filter, and to discover which column to pass to educa_preview_grades. The usage context is clear and actionable. It lacks an explicit when-not (e.g., 'use educa_dump_html when you need the raw source'), so the boundary against similar inspection siblings is left implicit.

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