Quaderno MCP Server

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

No annotations exist, so the description carries the full burden. It helpfully discloses the return content (tax rate, tax name, reverse-charge flag) which compensates for the missing output schema, but says nothing about edge cases such as jurisdiction-specific requirements, failure modes, or latency/auth considerations.

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 tight sentences: the purpose first, the return shape second. Every clause earns its place and nothing is padded.

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 states what comes back, and the 100%-covered input schema handles the inputs. It misses only operational edge cases (e.g. that postal code is mandatory for US) which the schema partly covers.

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 every parameter is already documented in the schema. The description only restates the main input categories (location, product type, tax ID) without adding syntax or value constraints, 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?

Specific verb+resource ('Calculate the applicable tax rate for a transaction') with an explicit basis (customer location, product type, optional tax ID). It is clearly distinguished in kind from its siblings (validate_tax_id, create_invoice), though it never names or routes against them.

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 by the description—you call it to determine a transaction's tax treatment—but there is no explicit when-to-use, when-not, or relationship to validate_tax_id, which an agent might otherwise confuse it with.

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 not state permission requirements, what happens on duplicate email/tax_id, whether tax_id is validated, or whether creation is idempotent — significant gaps for a mutation tool whose sibling validate_tax_id exists.

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 short sentences, front-loaded with the core action and scope, with zero filler. Every clause contributes.

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 13-parameter mutation tool with no output schema and no annotations, the description is adequate but thin. It conveys what is created and its downstream use, but omits permissions, failure modes, and any hint of the returned identifier an agent would need to reference the contact later.

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 every parameter (including the kind enum and the first_name-as-company-name nuance) is already documented in the schema. The description adds no parameter-level meaning beyond that, so the baseline of 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?

Names a specific verb and resource ('Create a new contact') and clarifies the scope with '(customer or company)'. It does not explicitly differentiate itself from siblings like create_invoice, though the mention that contacts are referenced when creating invoices gives a loose relational cue.

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 second sentence implies the tool is used when you need a contact to later attach to invoices, which gives implied context. However, there is no explicit when-to-use/when-not guidance, no prerequisites, and no 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?

With no annotations, the description carries the full behavioral burden. 'Tax-compliant' implies tax handling, but there is no disclosure of auth requirements, whether the invoice is created as draft or finalized, idempotency, or side effects such as contact auto-creation when contact_name is supplied.

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 tight sentences, front-loaded with the core action, with zero filler. It is efficient, though the second sentence largely duplicates schema content.

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?

A mutation tool with 8 parameters, no annotations, and no output schema, so the description should say more about the response or lifecycle. Implicit coverage of the contact reference helps, but return value and post-creation state are left unstated.

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 all 8 parameters and the baseline is 3. The description restates the item structure (description, quantity, unit price) and the contact lookup behavior, but adds no format, default, or constraint detail beyond the 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?

States a specific verb and resource ('Create a tax-compliant invoice in Quaderno') and outlines what an invoice contains, distinguishing it from list_invoices and create_contact by implication. It never names a sibling explicitly, so the differentiation is only implicit.

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 offers no when-to-use or when-not guidance, and no prerequisites (e.g. contact must exist first, or that create_contact precedes this). The contact-by-ID-or-name note is parameter help, not usage routing, so there is effectively no alternative-selection 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?

No annotations are provided, so the description carries the full behavioral burden. It does not state that the operation is read-only, whether results are paginated (only the schema hints at page), auth requirements, or what the response contains. The filter context is thin for a tool with zero annotation coverage.

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 tight sentences with the core purpose front-loaded and filtering scope second. No filler, though the second sentence largely echoes schema fields.

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-required-param list tool the description is adequate, but with no output schema and no annotations it omits return shape, pagination behavior, and safety profile. It covers the minimum needed to invoke, not the full behavioral picture.

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 all four params (q, date, page, state) are already documented. The description restates three of them (contact name, state, date) but ignores pagination and adds no syntax or format detail beyond the schema. 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+resource: 'List invoices from your Quaderno account.' An agent can distinguish this from create_invoice and create_contact by the 'List' verb. It stops short of differentiating scope from any sibling list tool, but none exists here.

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 sentence 'Supports filtering by ...' implies when the tool is useful, but there is no explicit when-to-use guidance or exclusion relative to siblings (e.g., create_invoice, calculate_tax). Usage is only implied by the read-oriented 'List' verb.

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 behavioral burden and falls short. It does not say whether validation is a pure format/checksum check or a live registry lookup, what happens with an unsupported country, whether it throws or returns a boolean/status, or whether auth is required. Only the supported-region list adds any behavioral context.

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 compact sentences with no filler, and the core action is front-loaded. It could be tightened slightly, but nothing is wasted.

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 and no annotations, the description must explain what a validation result looks like and what unsupported or invalid input produces, and it does neither. For a pure-input validation utility whose only value is its verdict, this is a substantial 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 coverage is 100%, so both parameters are documented in the schema and the baseline is 3. The description adds real meaning for the country parameter by enumerating the supported jurisdictions (EU, UK, Switzerland, Australia, New Zealand, Canada/Quebec), which effectively communicates the valid range of country inputs.

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 specific verb (validate) and resource (tax identification number) and enumerates the identifier types covered (VAT, GST, ABN). It does not explicitly differentiate itself from siblings like calculate_tax, but those are clearly different operations, so the tool 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 guidance on when to call this tool versus the siblings — e.g. whether it should be used as a preflight check before create_invoice or create_contact. Usage is only implied by the tool name, with no conditions, prerequisites, or alternatives named.

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