Portal Haras

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds important behavior beyond annotations: it explicitly says the tool does not send anything, and that passing 'consulta' returns a WhatsApp link with a prewritten message for the person to send themselves. It does not describe auth or rate limits, but for this read-only contact lookup the added context is solid.

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 the core purpose and followed by the key conditional behavior. Every sentence carries useful information and there is no redundant restatement of annotations or 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?

Given one optional parameter, no required parameters, and no output schema, the description is largely complete: it states what channels are returned and what extra value 'consulta' produces. It does not detail the return shape beyond listing channels, but that is a minor gap for a simple read-only contact 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 description coverage is 100%, so the schema already defines the optional 'consulta' string with an example. The description adds conditional meaning: when 'consulta' is passed, the return includes a WhatsApp link with that message already written. That is useful semantic value beyond the schema's field description.

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 clearly states the tool returns contact and visit channels (WhatsApp, email, sales office, hours, map), which is a specific resource. It does not explicitly differentiate from the sibling tools like get_page or get_project_info, so it lands at 4 rather than 5.

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: use this when the user needs contact channels or wants to schedule a visit. There are no explicit when-not conditions or named alternatives among siblings, so it meets the minimum viable threshold but leaves selection guidance implicit.

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 openWorld=false, so safety is covered. The description adds genuine value beyond them by specifying the return payload format (full markdown text) — especially useful since there is no output schema — and by disclosing the slug dependency. It omits error behavior when a slug is missing, keeping it from a 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?

A single sentence that front-loads the verb and return type before the input source. Every clause earns its place: what is returned, in what format, for which two content types, and where the slug comes from.

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 fetch tool with annotations covering its safety profile and no output schema, the description states the return format, the input origin, and the two content variants — enough to invoke it correctly. The only gap is error/edge behavior (invalid or nonexistent slug), which is minor for this tool class.

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 50% schema coverage, the description compensates by clarifying what the two content kinds are: 'una landing por rubro' versus 'un artículo del blog', which maps onto the otherwise-undocumented 'blog'/'locales' enum values. The slug parameter's meaning is also reinforced by tying it to search_content/list_pages, though exact enum-to-value mapping is left implicit.

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: 'Devuelve el texto completo en markdown' of either a landing-by-category or a blog article, keyed by slug. It distinguishes itself from siblings by naming search_content and list_pages as the tools that supply the slug, implying the search-then-fetch workflow, though it stops short of an explicit contrast (e.g. 'unlike search_content, returns the whole document').

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 parenthetical '(lo dan search_content y list_pages)' tells the agent exactly when this tool is the follow-up step: after obtaining a slug from one of those feeders. There is no explicit when-not guidance or exclusion rule, so it falls short of a 5, but the sequencing context is 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 readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds something annotations cannot: the shape of each record (outlet, date, title, summary, link), which substitutes for the absent output schema. It does not say whether results are ordered, paginated, or how many are returned.

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 sentence with no filler. The entity scope is stated first and the field list second, so the important constraint is front-loaded; only the lack of a leading action verb slightly weakens the opening.

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 takes on the burden of describing return values and does so by enumerating the five fields. Given a zero-param read-only tool with full annotation coverage, the remaining gaps — ordering and result volume — are minor rather than blocking.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; baseline 4 applies. The description correctly implies an unfiltered fetch of the whole press list, which is consistent with the empty schema.

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 identifies the exact resource returned — press/media mentions that reference 'Portal Haras' or 'Paseo del Haras' — which lets an agent distinguish it from siblings like get_page or search_content. It is phrased as a noun phrase describing the dataset rather than a verb-led statement of action, but the resource is unambiguous.

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?

There is no statement of when to call this tool versus alternatives such as search_content, and no mention of freshness, scope limits, or whether the full set is always returned. For a zero-parameter tool the intent is inferable, but the description contributes no usage guidance at all.

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, idempotentHint, openWorldHint=false, and destructiveHint=false, so the safety profile is covered. The description adds useful context that the data is current ('vigentes') and authoritative ('fuente de verdad'), though it does not discuss error behavior or response shape.

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?

It is a single front-loaded sentence beginning with 'Datos vigentes' and then listing the relevant domains. It is dense but every listed domain earns its place; structure could be slightly improved with separators or bullets, but there is no filler.

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 parameterless, read-only lookup tool with annotations and no output schema, the description is largely complete: it states the data domains and authoritative status. It does not describe the response structure, but no output schema exists and the enumeration gives an agent enough to know what will be returned.

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?

The tool has zero parameters, so there are no parameter semantics to explain. The baseline for a parameterless tool is 4, and no schema gaps need compensation.

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 names the specific resource (Portal Haras project data) and enumerates the exact domains covered: units, surfaces, price per m², projected rent, financing, delivery, location, environment, eligible sectors, and developer. This is clearly distinct from Contact, Page, Press, and Content-list tools, though it does not explicitly name a sibling alternative.

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 phrase 'Es la fuente de verdad para cualquier cifra' gives a clear usage rule: use this tool for project figures and factual project data. It does not provide explicit when-not-to-use guidance or name sibling tools, but the intended context is 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 readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely new behavioral context — sort order (newest first) and the shape of returned fields (slug, título, descripción, fecha, URL) — but says nothing about pagination behavior, default page size, or result caps.

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 dense sentence that front-loads what is listed, then the enum mapping, then ordering, then returned fields. No filler; every clause carries information, though the returned-field list could arguably be trimmed given it is implied by the tool's nature.

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 previews the returned fields and ordering, which is exactly what the agent needs. The remaining gap is pagination: limit/offset exist in the schema but neither structure nor defaults (50, max 200) are surfaced in prose.

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 33%; only 'kind' has a description and it is terse ('Qué listar.'). The description does compensate for the most important gap by mapping enum values to meaning (kind=locales → landings, kind=blog → blog articles), but limit and offset remain undocumented in both schema and description, and offset-based pagination semantics are not explained.

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 two concrete resources: landings by rubro (kind=locales) and blog artículos (kind=blog), plus the ordering and returned fields. An agent can immediately tell what it retrieves, though it never names or distinguishes itself from siblings like get_page or search_content.

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 through the kind enum mapping; there is no explicit guidance on when to use this instead of search_content (e.g., free-text lookup) or get_page (single item). The agent must infer the boundary from sibling names alone.

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, idempotentHint, non-destructive and closed-world, so the safety profile is carried. The description adds value beyond that by disclosing the return shape (slug, título, descripción, URL) and the fact that results are relevance-ranked summaries rather than full documents — important with no output schema.

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 defines scope and content, the second defines output and the handoff to get_page. Everything an agent needs is front-loaded.

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?

Only one required parameter, rich annotations and a description that spells out the returned fields in lieu of an output schema. The one gap — limit behavior — is minor and bounded by the schema's min/max.

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 67%: query and kind are documented in-schema with an example and enum values, while limit has no description anywhere. The description reinforces the kind split and the topical scope of query, but adds no syntax, ranking or limit behavior, so the baseline 3 for mostly-covered parameters stands.

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 (busca) and two concrete resources — landings por rubro and blog articles on portalharas.com — with topical examples that pin down the content domain. It also distinguishes itself from the sibling get_page by noting that full text is fetched elsewhere, so an agent can route without opening either 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?

Explicit routing to get_page for full text gives a clear 'use this when you only need the relevant pages' rule. The split between blog and landings by rubro is also signposted, though the description never contrasts itself with list_pages, leaving one sibling's boundary implicit.

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