Siigo Latam

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

No annotations, so the description carries full burden. It reveals the return shape (slug, title, excerpt, author, date, category, URL, JSON-LD) and the silent-failure behavior of high limits is documented in the schema rather than the description. No auth requirements, rate limits, or empty-result caveats in the description itself.

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?

Well-structured: purpose, return shape, usage context, and concrete examples. Slightly long with the example calls, but every sentence adds value.

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?

Complete for a read-only list tool with a rich schema. The description covers purpose, usage, return fields, and examples. No output schema exists, so the return-field enumeration is valuable. Minor gap on pagination or empty-result behavior.

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 parameters are fully documented in the schema. The description adds example calls that clarify typical usage patterns, but no semantics beyond what the schema provides. 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 verb+resource (returns Siigo blog articles) with clear scope (recent, per-country, optional topic). Distinguishes from sibling data tools like get_products and get_compliance_info by focusing on blog 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?

Explicitly says 'Use this when the user wants up-to-date Siigo perspectives on accounting, taxes, PYMEs, fintech or product launches,' giving clear context. No explicit when-not or named alternatives, but the domain is specific enough that usage is unambiguous.

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?

With no annotations, the description carries the full burden and does well: it discloses the exact return shape (title, summary, last-updated date, source URL, JSON-LD), and states the default behavior when regulation is omitted (50 latest items). It does not mention auth or rate limits, which is a minor gap for a read-only lookup.

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-loaded with the purpose, then return shape, then usage and examples. Slightly padded by the long parenthetical list of regulations, which partially repeats content already conveyed by the return-shape sentence and the schema examples.

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, but the description adequately explains the returned fields and the default result size, plus working example calls. An agent has everything needed to invoke it correctly.

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, but the description adds concrete invocation examples ('{"country": "MEX", "regulation": "CFDI"}') that demonstrate the full-list vs. narrow-down distinction beyond the per-parameter schema docs.

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 ('Returns tax-and-regulatory compliance information') and enumerates the actual regulatory content for Colombia and Mexico. This is clearly distinguishable from siblings like get_articles or get_products.

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?

Explicitly states when to use it ('when the user asks about Siigo's compliance posture or specific regulations'). It does not name alternative tools or exclusion conditions, but no sibling overlaps meaningfully with this niche.

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?

No annotations are provided, so the description carries the full behavioral burden. It usefully discloses provenance (read from the country's home page graph) and the localised data key path, but says nothing about failure modes, availability beyond the schema's Actives note, or caching/limits for a live scrape-backed read.

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 return payload before the usage guidance and example, so an agent gets the essentials first. It is somewhat long and leaks internal jargon (ContentProviders:{country}:Webapp:OrganizationSlug) that does not help tool selection.

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 compensates by enumerating the returned fields (legal name, URL, logo, sameAs, address, phone, founding date) and the accompanying JSON-LD graphs. It is largely complete for a simple one-parameter read.

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 country parameter is fully documented with format and examples, so the schema already does the heavy lifting (baseline 3). The description only adds a redundant example call.

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 (returns canonical Organization data for Siigo in a country) and enumerates the exact fields returned. The note that the data comes from the country home page, 'the only page that publishes the Organization graph,' implicitly separates it from the generic get_page_structured_data sibling.

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 an explicit condition: 'Use this when the agent needs trustworthy company facts to cite Siigo as a source.' That is a clear trigger, though no exclusion or named alternative (e.g. when to prefer get_page_structured_data) is offered.

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?

No annotations are provided, so the description carries the full burden. It does disclose useful edge behavior ('Pages with no JSON-LD still return title + seo with an empty jsonLdGraphs array'), but says nothing about authentication, rate limits, caching, or pagination for a network-backed read 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?

Three tight sentences, front-loaded with what is returned before the usage hint and the example. No filler, though the inline example call is arguably redundant with the schema's own examples.

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 must characterize the return value, and it does: JSON-LD graphs plus SEO metadata, and the degraded shape (title + seo with empty jsonLdGraphs) when nothing is found. It could still say more about the full response envelope, but it is adequate for a two-parameter read 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% and the schema already documents both parameters (slug pattern, real slug list, country ISO code, unknown-slug behavior). The description's example call {'country': 'COL', 'slug': 'facturacion-electronica'} is helpful but largely duplicates schema examples, so baseline 3 applies.

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 ('Returns') and resource ('curated JSON-LD structured data graphs ... for a Siigo landing page, plus SEO metadata') and even enumerates the schema types produced (Service, Product, Offer, Review, FAQ, Breadcrumb). That is far more specific than the sibling names alone, though it never explicitly contrasts itself with get_articles/get_products/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?

Gives a clear triggering condition: 'Use this when the user asks about a specific Siigo product or topic and you want canonical, schema.org-ready data.' It does not name an alternative tool or state when NOT to use it, so it stops short of a 5.

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?

No annotations are provided, so the description carries the full behavioral burden. It does disclose source ('read from schema.org Product graphs'), default slug behavior, and that an empty array means no published Product JSON-LD, which is useful. However, it does not state whether it is read-only, whether it hits the network, caching behavior, or how countries not in the active list are handled beyond the schema's note.

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 purpose, then when-to-use, then example, then edge case. Four sentences, each doing work, though the schema.org source detail is somewhat technical for an agent. No significant waste.

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 lookup with no output schema, the description covers purpose, trigger, example invocation, and an important edge case (empty array semantics). Missing only a note on whether the call is side-effect free. Adequate for the tool's complexity.

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 both parameters in detail (slug defaults, country whitelist). The description adds an example call and mentions the default slug, but these largely repeat the schema's own examples and defaults. 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 verb+resource ('Returns Siigo's catalog of products/plans') and the scope (per country, price/currency/features). Sibling tools are named in the sibling list but the description does not differentiate itself from get_page_structured_data, which it is tightly coupled to.

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?

Explicitly says 'Use this when the user asks about pricing, plans, or what's included in each tier,' giving clear triggering context. No explicit when-not condition or direct routing to an alternative like get_page_structured_data.

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?

No annotations, so the description carries the full burden — and it discloses a genuinely important environment-specific trap: the COL shell has search disabled and returns an empty items array, with a recommended workaround. It stops short of describing pagination, result limits, or ranking behavior, which leaves some operational gaps for a search 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?

Front-loads purpose, then trigger, then example, then the COL caveat — a sensible information hierarchy. The example call is somewhat redundant with the schema's examples, but nothing is padded or confusing.

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 does state the return shape (matching pages, posts, and resources) and warns that COL returns an empty items array, which is the critical thing an agent needs. Pagination and result-count behavior remain unaddressed.

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 both parameters carry detailed descriptions with pattern/maxLength and examples, so the schema does the heavy lifting. The description's inline example call largely duplicates the schema's own examples rather than adding new parameter meaning.

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 ('Full-text search against Siigo's curated content for a country') plus the returned entity types (pages, posts, resources). It also implicitly distinguishes itself from the more specific siblings by framing itself as the fallback topic 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?

Gives an explicit trigger ('when the user mentions a topic you don't have a more specific tool for') and names concrete alternatives (get_articles, get_compliance_info) for the COL case. Both when-to-use and when-not-to-use are covered.

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