embalses

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description restates the sort behavior that the orden enum already implies and adds little new behavioral context such as pagination or result limits.

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?

A single front-loaded sentence describing filters and ordering, followed by tightly chosen example queries. Efficient, though the example list is slightly long for the value it adds.

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 6-parameter tool with no output schema, the description covers the filter/sort surface and usage scenarios adequately. The main gap is that the limite parameter and result-volume behavior go unmentioned.

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 only 50% schema description coverage, the description compensates well by naming the four filter fields and the ordering modes. It adds meaning beyond the schema for texto, provincia, comunidad, cuenca, and orden, though it never explains the limite cap.

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 (Lista) and resource (embalses de España), and enumerates the filter dimensions (nombre, provincia, comunidad, cuenca) plus the three sort modes. This clearly distinguishes it from estado_embalse, historico_embalse, and resumen_agua_embalsada, which cover status/history/summary rather than search.

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?

Three concrete example queries ('¿qué embalses hay en Huesca?', 'los pantanos más vacíos de Andalucía', 'embalses de la cuenca del Segura') strongly imply when to reach for this tool. It does not explicitly exclude sibling tools, but the examples make the intended use clear.

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 declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description adds real behavioral context beyond that: the ~120-station scope, the comparison baseline (same week's median since 2001), and the inclusion of prior-year same-week values and series extremes.

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 core output (weekly average flow, comparator, scope) before the parameter-behavior clause. It is dense but every clause carries information; only mild trimming would be possible.

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 read-only, two-parameter retrieval tool with no output schema, the description is nearly complete: it conveys the data source, units, comparison baseline, station coverage, and how parameters shape the response. A note on return granularity or units for the extremes would close the remaining gap.

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 `cuenca` and `nombre`, including example formats. The description reinforces how each parameter changes the result (station vs. river, single basin vs. national summary) but adds little syntax or format detail beyond the schema, warranting the baseline 3.

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 resource and metric: weekly average flow (m³/s) of Spanish rivers at ~120 MITECO gauging stations, benchmarked against the seasonal median since 2001. The river-flow domain is clearly distinct from the reservoir-oriented siblings (estado_embalse, historico_embalse), so an agent can route correctly.

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?

Explains the two calling modes concretely: with `nombre` you get a station or all stations of a river; without it you get a Spain-level or basin-level summary highlighting the driest and highest rivers. It gives clear context but no explicit exclusions or named alternatives among siblings.

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 declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuine behavioral context beyond that: it discloses the tolerant name matching ('con o sin embalse de/pantano de/pantà de y sin tildes') and that the result includes a link to the embals.es record, neither of which is in the annotations.

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: the first front-loads the resource and the returned fields, the second handles input tolerance. No filler, and the most decision-relevant content (what it returns) leads. Slightly dense but well organized.

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 usefully enumerates the returned fields and the data date, and both input parameters are documented. It stops short of covering ambiguity/error behavior when a name matches multiple reservoirs or none, which would be the remaining gap for a lookup 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 coverage is 100%, so the baseline is 3. The description earns above baseline by documenting the accepted input forms for 'nombre' (optional prefixes, accent-insensitive, with examples) that the schema's minimal example does not cover; 'provincia' is left to the schema text.

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 description gives a concrete resource ('un embalse de España') and enumerates exactly what is returned: fill percentage, stored water and capacity in hm³, weekly variation and data date. The phrase 'Nivel actual' implicitly distinguishes it from historico_embalse, but no sibling is named explicitly.

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: 'Nivel actual' signals a current-snapshot tool rather than the historical or search siblings, and 'provincia... solo para desambiguar' hints when the second parameter matters. There is no explicit when-to-use, when-not-to-use, or named alternative, so an agent must infer routing from the sibling names.

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 declare read-only, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds real value beyond that: the official data provenance (MITECO), the since-1988 temporal span, and a breakdown of what the historical series contains. It omits return format/pagination, keeping 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, zero filler: the first front-loads what the tool returns, the second front-loads the questions it answers. Every clause earns its place.

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 usefully describes the returned series, data source, and temporal coverage, and all parameters are documented in the schema. Disambiguation guidance for 'provincia' is left to the schema text, so it is strong but not exhaustive.

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%, so all three parameters are already documented, and the description adds little syntax or format detail. It only loosely implies the years-back window via 'el nivel en la misma semana de cada año anterior', without tying that to the 'anos' parameter explicitly, 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 resource (weekly evolution of a reservoir) and its exact content: recent weeks, same-week values for each prior year, and period max/min, sourced from MITECO since 1988. This scope is instantly distinguishable from siblings like estado_embalse (current state) or buscar_embalses (search) 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?

Provides explicit use-case framing via the questions it answers ('is it fuller than last year?', 'when was it this low?'), which tells the agent when this tool is the right pick. It does not, however, name alternatives or state when NOT to use it, so it stops short of full routing guidance.

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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context beyond that by enumerating the returned report contents (weekly variation, fullest/emptiest reservoirs, year-over-year and 10-year comparisons), which sets expectations for the response.

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?

A single information-dense sentence that front-loads the core purpose (total and fill percentage) before listing supplementary returns. It is grammatically heavy but contains no filler clauses that could be dropped.

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 correctly carries the burden of describing return values and does so thoroughly. Only 2 parameters (0 required), and the scope/name logic is adequately conveyed, leaving little an agent needs that isn't present.

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 only 50%: 'nombre' is documented in the schema while 'ambito' has an enum but no description. The description compensates partially by naming the four scopes (España, comunidad autónoma, provincia, cuenca hidrográfica) that map to the 'ambito' enum and by implying 'nombre' identifies the chosen region, reaching the baseline for the coverage gap.

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 resource and scope: aggregate reservoir water (total volume, fill percentage) for Spain or a region/province/basin. An agent can tell this is a summary/aggregate tool. However, it never references the sibling tools (buscar_embalses, estado_embalse, historico_embalse), so differentiation is left to inference.

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 says what the tool covers but never states when to use it versus the sibling search/status/history tools. No exclusions, prerequisites, or alternative-selection guidance are given; usage is only implied by the summary nature of the output.

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, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds genuinely useful behavior: a ten-day measurement cadence with 3-5 weeks of lag, and the four CDI severity categories — latency is exactly the kind of context an agent needs to interpret freshness.

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 what is measured and by whom, then the categories, then cadence and the default behavior. Dense but every clause carries information; the only slightly redundant piece is repeating the empty/'España' behavior already in the schema.

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 single-parameter read-only tool with no output schema, the description supplies the domain, the indicator categories and the data latency, which is enough to call and interpret it correctly. It stops just short of describing the actual return shape (e.g. percentages per category per region).

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 `lugar` parameter is fully documented in the schema. The description only restates the empty/'España' default and adds that omitting it also returns the most affected provinces — marginal value beyond the schema, so baseline 3.

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 resource (drought status by region per Copernicus CDI) and the exact scope of the answer (% of territory in vigilancia/aviso/alerta/recuperación). This is clearly distinguishable from the reservoir and river-flow siblings 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?

Usage is implied rather than stated: the description explains the default behavior when `lugar` is omitted, which hints at how to call it, but never says when to prefer this over the embalse/caudal siblings or what conditions make it inappropriate.

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