snapshot_status

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the read-only safety profile is covered. The description adds genuine behavioral context beyond annotations: it explains the live_check state machine (pending/unchanged/updated/unavailable) and the failure behavior of 'unavailable' (no Chrome, no display, no network — keeps serving the snapshot). This non-obvious 'fallback to stale data' behavior is exactly the kind of transparency that helps an agent.

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?

The description is front-loaded with the one-line purpose statement followed by a structured field-by-field breakdown. Each field earns its place by explaining possible values and conditions (e.g., when guia_808 appears). Slightly verbose but well organized; the bullet-style per-field formatting makes it 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?

For a zero-parameter status tool, the description is largely complete: it documents all three response fields, their value spaces, and edge cases. The main gap is the absence of a 'when to use this' note connecting it to the sibling content tools, which would round out the context. The output schema covers return-value structure, so the absence of explicit return-format detail is not a penalty.

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?

With zero parameters, the baseline is 4 and the description correctly focuses on the response fields (captured_at, live_check, guia_808) instead of parameters. It adds semantic meaning by enumerating the possible live_check values and their meanings, and clarifying that guia_808 appears only when the guide is loaded. The output schema exists, but the description enriches what those fields represent.

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?

The opening line 'Origen y frescura de los datos servidos' (origin and freshness of served data) states the purpose clearly, and the field-by-field explanation of captured_at and live_check makes it evident this is a status/metadata inspection tool. It distinguishes well from the content siblings (list_categories, get_measure, search_measures, etc.) which operate on data rather than on the freshness/origin of what's being served.

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 provides no guidance on when to use this tool versus alternatives. It never mentions that this should be checked before trusting data, nor does it exclude any scenarios or reference sibling tools. Given the sibling set contains audit/data tools that depend on this same underlying data, explicit usage context (e.g., 'check this before interpreting requisitos_articulos') would significantly help.

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