accounting-mcp

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

With no annotations provided, the description carries the full burden. It states that the tool updates AccountCode and TaxType, which indicates mutation, but it doesn't disclose other behavioral aspects like idempotency, error handling, whether it operates on the entire array atomically, or any side effects. For a mutation tool, this is insufficient.

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 description is a single, efficient sentence that immediately communicates the action and outcome. No filler words.

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?

The tool has no output schema and no annotations, so the description must provide a complete picture. It fails to mention the return value, any pre-conditions beyond 'confirmed', or how the request is processed (e.g., batch behavior). As a side-effecting tool with a nested array parameter, this is too sparse.

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?

Although the schema already provides descriptions for both parameters (100% coverage), the tool description adds meaningful context by explaining that applying a category affects AccountCode and TaxType, giving semantic weight to the category_code field. The api_key_hash is adequately described in 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?

The description uses the specific verb 'apply' with a clearly defined resource ('Portuguese tax categories' to 'Xero transactions') and states the concrete effect (updates AccountCode and TaxType). This clearly distinguishes it from sibling tools like 'categorise_expenses' which handles the initial categorization.

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 does not provide any guidance on when to use this tool versus alternatives such as 'categorise_expenses' or 'confirm_reconciliation'. There are no explicit prerequisites, exclusions, or scenarios beyond the word 'confirmed', which implies a prior step but is not elaborated.

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 provided, the description carries the transparency burden. It does disclose one meaningful behavioral trait: automatic detection of intra-community B2B reverse charge. However, it doesn't mention return format, potential errors (e.g., invalid category/region), or how missing optional parameters affect behavior. This is partial disclosure, not comprehensive.

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 description is extremely concise—two sentences, front-loaded with the core action. Every sentence adds value: the first identifies the core calculation and supported regions, the second highlights a key automatic behavior. No wasted words.

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?

The tool has five parameters and no output schema, so the description should provide more operational context. It explains the input dimensions and one behavioral nuance (reverse charge), but it doesn't clarify what the tool returns (e.g., single VAT amount, breakdown, total with VAT) or how it handles ambiguous inputs like missing category. This is adequate for simple use but leaves gaps for an AI agent trying to predict exact output.

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 schema descriptions provide full coverage (100%) for all five parameters, so the description doesn't need to compensate. The description adds some context by mentioning 'category' and 'region' but doesn't elaborate on parameter interactions or constraints beyond what the schema already states. Baseline 3 is appropriate given the high schema coverage.

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's function with a specific verb ('Calculate') and resource ('Portuguese VAT'), and adds valuable scope modifiers (amount, category, region, and the special cases of Mainland/Azores/Madeira and intra-community B2B reverse charge). This makes it distinct from the unrelated sibling tools (e.g., categorise_expenses, draft_invoice).

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 gives clear context for when to use the tool: for Portuguese VAT calculations with specific regions and B2B scenarios. It does not explicitly list exclusions or alternatives, but since none of the sibling tools perform VAT calculations, the intended use is evident. It falls short of a 5 because it doesn't explicitly state when not to use it or direct users to alternatives.

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 provided, the description carries the full burden of behavioral disclosure. The verb 'suggest' clearly indicates a non-destructive, read-only operation, and the expected outputs (category, VAT tier, deductibility, VAT breakdown) are listed. It could be more explicit that no data is written to Xero, but the word 'suggest' strongly implies this.

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 description is two sentences, front-loaded with the core purpose and followed by the return values. Every word earns its place; there is no redundancy or 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?

There is no output schema, so the description appropriately explains what the tool returns (category, VAT tier, deductibility, per-transaction breakdown). It covers the purpose, scope (uncategorised expenses), and output sufficiently for an agent to decide whether to invoke it.

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 baseline is 3. The description does not add parameter-specific semantics beyond what the schema already provides, but it does not need to since all parameters are fully documented in 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?

The description uses a specific verb+resource construction: 'Suggest Portuguese tax categories for uncategorised Xero expenses,' which clearly distinguishes it from siblings like apply_categories and calculate_vat. It also states the scope (uncategorised expenses) and the return payload.

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 'for uncategorised Xero expenses' provides clear context indicating this is for a pre-categorisation step, implicitly distinct from apply_categories. However, it does not explicitly name alternatives or say when not to use it, so it falls short of a perfect score.

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 states the core behavior (marking transactions as reconciled) but does not disclose side effects, idempotency, error handling, or permission requirements. While the primary action is clear, it lacks depth about what happens during the operation.

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 with no filler. The first sentence states the action, the second clarifies the effect. Highly efficient.

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 two-parameter tool with no output schema, the description is mostly adequate. It omits any reference to workflow prerequisites (e.g., running reconcile_transactions first) or outcomes, but the core functionality is sufficiently described given the tool's simplicity.

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%, with both parameters well-described in the schema. The description text does not add additional parameter semantics beyond what the schema already provides, so the baseline score 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?

The description uses a specific verb 'Apply' with the resource 'confirmed reconciliation matches' and explicitly states the outcome ('Marks matched bank transactions as reconciled'). It clearly differentiates from sibling tool 'reconcile_transactions' by indicating this tool applies already-confirmed matches rather than performing the reconciliation.

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 implies the tool is used after matches are confirmed, as it says 'Apply confirmed reconciliation matches'. However, it does not explicitly mention alternatives or when not to use it, though the context of the sibling 'reconcile_transactions' suggests a prior step.

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 transparency burden. It discloses that the tool creates a persistent draft in Xero and returns line totals and tax amounts for review, making the side effect and review workflow clear. It does not mention pitfalls like cleanup or rate limits, but the core behavior is transparent.

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, well-structured sentence that front-loads the purpose and includes the key output information. Every word earns its place; no filler or redundancy.

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?

The tool is moderately complex with 8 parameters, but the schema covers all parameter details. The description provides necessary context about the draft status and return values (line totals and tax amounts), which is especially useful since there is no output schema. Slightly more detail about the draft lifecycle or error conditions would make it fully complete.

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 input schema has 100% description coverage for all parameters, so the schema already provides full meaning. The description adds minimal parameter-level insight beyond the schema, such as implying VAT preview behavior through tax categories, but does not elaborate on specific parameters.

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 uses a specific verb and resource: 'Create a DRAFT invoice in Xero'. It clearly distinguishes from sibling tools like send_invoice by emphasizing 'draft' and 'before sending'.

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 conveys the intended usage context: creating an invoice for review before sending. It does not explicitly name alternatives or exclusions, but the draft/review framing makes the appropriate use case 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?

With no annotations provided, the description carries full burden. It does add useful behavioral context (indirect method for cash flow, SAF-T hints for VAT), but it does not state whether the operation is read-only, what output format to expect, or any side effects, leaving gaps.

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, well-structured sentence that front-loads the core purpose and then packs in the specific report types and key details without any fluff. Every word 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?

For a tool with 4 parameters, no output schema, and no annotations, the description does a solid job of conveying essential use cases. It could be more complete by mentioning the output format or data source (Xero), but the schema and description together are sufficient for correct invocation.

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?

All parameters are already described in the schema (100% coverage), so the baseline is 3. The description adds value beyond the schema by clarifying that 'cash_flow' uses the indirect method from balance sheet deltas and that 'vat_summary' includes Portuguese SAF-T filing hints, which aids parameter selection.

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 uses a specific verb 'Generate' and names the exact resource 'financial report', then enumerates the concrete report types (P&L, Balance Sheet, Cash Flow, VAT Summary). This clearly distinguishes it from sibling tools like calculate_vat or draft_invoice.

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?

Listing the report types implicitly tells the agent when to use this tool (e.g., when a P&L is needed). However, there is no explicit exclusion or pointer to alternative tools, 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?

With no annotations, the description carries full responsibility for behavioral disclosure. It explicitly states that the tool returns server status and supports optional echo, which is transparent about its read-only nature. However, it doesn't describe the format of the status response or any edge-case behavior, leaving some gaps.

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 description is a single sentence with no filler. 'Health check' is front-loaded, followed immediately by the return value and the optional echo parameter, making it maximally concise and well-structured.

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 health-check tool with one optional parameter and no output schema, the description is sufficiently complete to inform invocation and expected behavior. It could specify the exact format of server status, but this is a minor gap given the tool's simplicity.

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% for the single 'echo' parameter, which is clearly described. The description merely repeats 'optional echo' without adding extra semantics beyond the schema, so the baseline score 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?

The description clearly identifies the tool as a health check that returns server status and optionally echoes a provided string. The verb 'Returns' and specific resource ('server status') make the purpose clear, and it's distinctly different from the sibling business-process tools.

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 explicit guidance on when to use this tool versus alternatives, but the purpose is simple and self-evident: use it to check server health. The lack of exclusions or alternative references results in implied usage, which meets the minimum viable threshold.

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. It discloses key behavioral traits by specifying confidence-scored output categories ('>=0.8 matched, 0.5-0.8 suggested, <0.5 unmatched'). This is valuable beyond the schema. It does not state whether the tool is read-only or has side effects, but given its matching/suggestion nature, this is a minor gap.

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 description is two sentences, front-loaded with the primary purpose, and the second sentence explains the output categories. Every word earns its place; there is no redundancy or unnecessary detail.

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?

The description explains what the tool does and its output format, but it does not clarify how bank statement lines are supplied (e.g., fetched automatically based on date range) or whether the operation has side effects. Given the absence of an output schema and annotations, this is a notable gap, so a score of 3 reflects the missing context.

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 baseline is 3. The description adds meaning by clarifying that the tool operates on bank statement lines and Xero transactions, which helps interpret the to_date and from_date parameters as applying to bank statement lines. This contextual enrichment justifies a score above baseline.

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's function: 'Match bank statement lines against unreconciled Xero transactions.' This uses a specific verb and resource, and the addition of 'Returns confidence-scored matches' further clarifies the output, distinguishing it from sibling tools like confirm_reconciliation.

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 provides clear context for when to use the tool—when there are bank statement lines to reconcile against unreconciled Xero transactions. It implicitly suggests this is for generating match suggestions, not finalizing them. However, it does not explicitly mention alternatives or exclusions, 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?

With no annotations, the description carries the full burden. It discloses the two-step behavioral trait (AUTHORISED status then email) and the target system (Xero). It does not mention reversibility or error handling, but the core side effects are transparently stated.

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 are front-loaded with the primary purpose, followed by the two-step clarification. Every word earns its place; no filler or redundancy.

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?

The tool is a mutation with no annotations and no output schema, so more detail is needed. The description explains the operation flow but omits prerequisites (e.g., invoice must be in draft state), failure scenarios, and return values. It is adequate but not complete.

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 adds no new parameter meaning beyond the schema's descriptions; it merely repeats the context. The schema already explains invoice_id and api_key_hash accurately.

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 authorises a DRAFT invoice and emails it via Xero, with a specific two-step process. This distinguishes it from siblings like draft_invoice and reconcile_transactions by naming the exact verb and resource.

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 implies usage context ('DRAFT invoice', 'authorise and email') and gives a clear trigger condition, but does not explicitly name alternatives or when not to use the tool. It is sufficient for basic selection but lacks explicit exclusions.

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