E-Invoice Map

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered. The description adds that records are sourced with an official source_url and a checked date, which is meaningful trust context, but it says nothing about freshness policy, ordering, or behavior for countries with no mandate.

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 parameter guidance; every clause carries information an agent needs and nothing is redundant.

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 optional parameter with an output schema and read-only annotations, the description covers format, default behavior, and the shape of each record. Minor gaps remain around error handling for invalid country values and result ordering.

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 0%, so the description must carry the parameter — and it does, specifying accepted forms (two-letter code such as 'be', 'de', 'ae', or a country name) and that omitting it returns all countries. It stops short of covering case sensitivity or unknown-country behavior.

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 (e-invoicing mandate dates) and its granularity (per country or all countries), plus the payload each record carries (source_url and check date). It does not explicitly distinguish itself from siblings like foreign_supplier_scope, but the purpose is unmistakable.

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?

'Leave it out for all countries' gives clear guidance on the no-argument case, but there is no statement of when to reach for this tool versus the related scope/provider tools, and no exclusions or prerequisites are mentioned.

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 useful context beyond that: the data source (Peppol Directory / OpenPeppol AISBL) and that each count carries the change since the previous day, which shapes how the agent should interpret results.

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, no filler, with what is measured and the change metric front-loaded before the parameter note. 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?

An output schema exists, so return shape need not be described; the description covers what is counted, the source, the daily-delta semantic, and the full parameter behavior. Nothing needed to call this correctly is missing.

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 0% and the param has only a null default, so the description carries the full burden — and it does: accepted values are a two-letter country code or 'all', and omission means all countries. That is exactly the semantics the schema lacks.

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 precise verb+resource: counts of businesses listed in the Peppol network directory, broken down per country with day-over-day change. An agent can tell this apart from lookup/provider siblings by the 'counts per country' framing, though 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?

It states that country is a two-letter code or 'all', and that omitting it returns every country, which is the only branching decision this tool has. It does not name alternatives or when-not-to-use, but for a single-purpose read tool the guidance is sufficient.

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, destructiveHint=false and openWorldHint=false, so safety is covered. The description usefully adds what the response will contain (meaning, usual causes, fix, and who is responsible for the fix), which is behavioral context beyond 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?

One dense sentence with the purpose front-loaded and examples placed immediately after the resource, so the format hint arrives before any schema lookup is needed. 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?

An output schema exists, so return values need not be spelled out, and the description still previews the four content sections of the answer. Complete enough for a one-parameter lookup tool; the only missing piece is guidance on invalid or unknown codes.

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 0% for the single required 'code' parameter, so the description carries the burden — and it does supply concrete example values that convey the expected code format. It stops short of stating the accepted code systems, case sensitivity, or behavior on an unrecognized code.

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 ('explain') and a specific resource (an e-invoice validation rule code), and even names the standard families the codes come from ('BR-CO-10', 'PEPPOL-EN16931-R120'). No sibling tool ('deadlines', 'providers', 'lookup_access_point') could be mistaken for this one.

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: an agent can infer it should call this when it has a validation error code in hand, but the description never says when to use it versus other routes, nor what to do if the code is unknown or unrecognized.

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 behavior. The description adds useful context beyond that: it draws from a 47-country table and includes official sources, which tells the agent the answer is authoritative and reference-oriented.

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 definition is a single dense sentence with the core scope front-loaded. It is efficient, though the clause about returned contents is slightly packed in and could be clearer.

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 an output schema present, the description need not explain return structure, but it does summarize the included fields. The main remaining gap is a brief note on country-code normalization or error handling, but overall the definition is sufficient for a safe lookup call.

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 0%, so the description must carry parameter meaning. It does by stating the country input accepts a two-letter code or an English name, which is essential for correct invocation. It does not describe invalid-input behavior, keeping it below a 5.

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 states a precise question-domain: whether a supplier with no establishment in a country must e-invoice there, plus the data returned (system, B2B status, foreign-supplier applicability). This is clearly distinguishable from siblings like deadlines or providers.

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 implied use case is clear from the tool title and description, but there is no explicit 'use this when' or comparison to sibling tools. An agent can infer it is a country-scoped lookup, but the routing guidance is only 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?

Goes well beyond the annotations (which already mark it read-only, idempotent, open-world, non-destructive) by disclosing a daily rate limit and the graceful degradation path when the limit is hit (answer points to the free web lookup). It also tells the agent that returned data includes certificate validity, which signals freshness-sensitive metadata rather than a live transaction.

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 core action and the identifier argument, followed by short, purposeful sentences on scope, rate limits, and the optional hint. The opening sentence is dense with a nested parenthetical and a colon-list, but nothing is 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 two-parameter lookup with an output schema already present, the description covers everything an agent needs: what input to supply, what comes back at a conceptual level, the read-only metadata scope, and the rate-limit failure mode. No significant gap remains.

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 0%, so the description carries the burden and mostly does: it explains the identifier with concrete examples (Belgian company number, Peppol ID 0208:0521875440) and defines country as an optional two-letter hint. It stops short of giving explicit format constraints or noting that country may disambiguate identifier collisions.

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 concrete verb and resource: find the access-point provider that receives a given business identifier's e-invoices on the Peppol network. It also enumerates the returned fields (provider organisation, SMP host, document types, certificate validity) and scopes the tool with 'Provider metadata only', which separates it from sibling tools like providers/provider that presumably list or manage provider records.

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?

Clearly frames the trigger condition: you have a business identifier (company number or Peppol ID) and want to know which access point receives its invoices. The 'Provider metadata only' clause functions as a scope exclusion, and the rate-limit sentence tells the agent what happens at the boundary, but no sibling tool is named as an alternative for related questions (e.g. provider catalogue browsing).

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 fully covered structurally. The description adds some domain context — that prices carry a source and check date, hinting at data freshness — but says nothing about what happens when the name is unknown, or about rate limits and result size.

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 that states the lookup key first and the returned payload second. No filler, no restatement of the title.

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 one-parameter, read-only lookup with an output schema that already documents return shape, the description covers purpose and payload scope adequately. The only real gap is the slug-vs-id naming mismatch and the lack of not-found behavior, which are minor at this 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 0%, so the description must carry the parameter, and it does partially: 'by name or id (for example 'billit')' gives a concrete example. However, the parameter is named 'name_or_slug' while the description says 'name or id', an unresolved slug-vs-id ambiguity that leaves format expectations unclear.

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 resource (one tracked provider), the lookup key (name or id), and enumerates the returned content: capabilities, formats, languages, free plan, and prices with source and check date. That is far more specific than the bare name 'provider' and implicitly separates it from the sibling 'providers' list tool, though it never names that sibling 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: an agent can infer this is the per-entity lookup to use once it has a name or id, versus the 'providers' sibling for enumeration. No explicit when-to-use, when-not-to-use, or alternative routing statement is present.

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?

The description adds meaningful behavioral context beyond the annotations: results are alphabetical by product name, ordering is independent of payment, and ads/affiliate links are excluded. These are non-obvious guarantees that help the agent trust the output. It does not describe edge cases such as countries with no tracked providers.

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 efficient sentences front-load the core purpose. The second sentence about payment neutrality is relevant but slightly tangential; overall it is well-sized with no wasted clauses.

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 simple, read-only, single-parameter listing tool with an output schema, the description covers purpose, parameter format, ordering, and output contents (page link). Minor gaps around empty-result behavior or country coverage prevent a 5.

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 0% schema description coverage, the description must compensate, and it does by specifying that the country parameter is a two-letter code. That is the key semantic detail absent from the schema. It does not mention case sensitivity or invalid-code behavior.

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 states the resource (tracked e-invoicing providers) and the scoping dimension (country), along with ordering and output contents. It clearly implies a listing operation, but it does not explicitly distinguish itself from the singular sibling tool 'provider', which likely returns a single provider's details.

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 to find providers in a given country. However, there is no explicit guidance on when not to use it or how it differs from the sibling 'provider' tool, leaving selection partly to inference.

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