LuckPanda Document Tools

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 'Read-only arithmetic' mostly restates structured data. The genuinely added behavioral context is the reducing-balance methodology, which tells the agent which amortization convention the numbers follow.

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 output-enumerating sentence plus a short qualifier — front-loaded and free of padding. Slightly fragmentary phrasing, 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?

An output schema exists and annotations fully cover the safety profile, so the description only needs to frame the computation. It does that adequately for a low-complexity arithmetic tool; the main omission is any usage/routing guidance.

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 years-vs-months precedence and the ISO 4217 default) is already documented in the schema. The description adds no additional parameter semantics, so the 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?

The description names a specific resource (reducing-balance loan) and enumerates the concrete outputs: monthly EMI, total interest, total payment, and a year-by-year schedule. It is clearly distinct from the GST/VAT/GSTIN siblings by domain, though it never uses an explicit verb like 'calculate' and leans on the noun-phrase form to convey the action.

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 when-to-use guidance, no mention of prerequisites, and no routing to or away from the sibling calculators (calculate_gst, calculate_vat). 'Read-only arithmetic' hints at the nature of the call but does not tell an agent when this tool is the right choice.

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 and destructiveHint=false, so the description's 'Read-only arithmetic' adds no new safety information. It does add domain behavior context (the intra-state vs. inter-state tax split), which is modestly useful but not beyond what a caller already knows from the enums.

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, front-loaded sentence with zero filler; the core operation comes first and the tax-split detail follows. Every clause carries meaning.

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 described. For a 4-parameter arithmetic tool with full schema coverage and complete annotations, the description supplies 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 description coverage is 100% and both enums are documented in-schema, so the parameters are already self-explanatory. The description echoes the add/remove and intra/inter semantics but adds no format or edge-case detail (e.g. treating rate as a string, default values) 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 (calculate) and resource (GST on an amount), and names the two distinct calculations it performs (add GST vs. remove GST) plus the CGST+SGST/IGST split. This clearly separates it from siblings like calculate_vat and calculate_emi.

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 explains when each mode applies (amount before tax vs. amount including tax) and when to expect CGST+SGST versus IGST, which is genuine usage guidance. It doesn't, however, explicitly route the agent away from calculate_vat/calculate_emi for non-India or non-GST cases.

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 cover the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false, openWorldHint=false), so "Read-only arithmetic" adds nothing and risks being redundant. The description does add the default-resolution behavior (UK and standard rate when unspecified), which is genuinely useful, but no further behavioral context such as rounding or currency handling is disclosed.

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 no waste, and the primary operation is front-loaded before the geographic defaults. 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 values need not be explained, and the description covers modes, country default and rate default well. Fully sufficient for correct invocation, with only minor room for rounding or currency-precision notes.

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 mode, rate, amount and country in detail. The description restates the mode and default behavior rather than adding syntax or format detail beyond the schema, so the 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 (calculate VAT) plus the resource and both directions of the operation (net→gross and gross→net). The geographic scope (UK default, EU/UAE by country) implicitly separates it from sibling calculate_gst, but no sibling is named explicitly, so it falls just short of a 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 by the geographic defaults: an agent can infer it should call this for UK/EU/UAE VAT rather than Indian GST. However, there is no explicit when-to-use/when-not-to-use statement and no pointer to calculate_gst as the alternative, leaving the choice to inference.

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 cover readOnlyHint, idempotentHint, destructiveHint, and openWorldHint=false. The description reinforces 'Read-only' and adds the crucial non-obvious constraint that no external lookup occurs, which is important for an agent to know this is purely structural validation. However, it doesn't mention error behavior (e.g., what happens if the GSTIN fails the check character) or rate limits.

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 concise sentences: purpose/scope front-loaded, then the critical negative constraint, then a one-word read-only tag. Every sentence earns its place with zero 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?

With an output schema present, return values need not be described. The description covers purpose, structural scope, negative boundaries, and read-only nature. It could be improved by mentioning the error/validation result behavior more explicitly, but it is largely complete for a simple single-parameter validation 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 coverage is 100%, so the schema fully documents the single gstin parameter including an example. The description adds no parameter-level detail 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 and resource ('Checks that an Indian GSTIN is well formed') and immediately scopes what is checked (15 characters, state code, PAN, check character), plus what it decodes. Clearly distinguishable from siblings like calculate_gst and find_hsn_code.

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 clearly delineates what the tool does NOT do: 'makes no lookup and does not confirm that the registration exists or is active.' This is strong negative guidance that routes the agent correctly. However, it does not name an alternative tool for actual GSTIN lookup or validation of registration status.

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: discloses the 7-day server-side storage under a random, unlisted/unindexed link id, that every call creates a new link (reinforcing idempotentHint=false), and that nothing is issued, numbered or sent. It also describes the response contents (totals with tax, missing required fields, ignored invalid parts). This is exactly the kind of side-effect disclosure a mutation tool needs.

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 purpose, then return values, then side effects, then the no-issue constraint and input rule — a logical ordering with little waste. It is somewhat long, and enumerating the five document kinds duplicates the enum already in the 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?

For a tool with a nested-object schema and an output schema, the description covers what an agent needs: what is validated, what comes back, storage side effects, and the constraint that nothing is issued. Return-value explanation is technically redundant given the output schema but harmless.

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 nested schema carries extensive per-field documentation, so the baseline is 3. The description adds only the input-integrity rule about not inventing details; it contributes no syntax, format or default information 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 (validate a document, return editor_url that opens it prefilled in the LuckPanda editor) and enumerates the supported document kinds. It is clearly separable from the create_document_pdf sibling because it produces a link, not the PDF itself, and explicitly says nothing is issued, numbered or sent.

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 clear context for use ('person can review, edit and download') and an explicit constraint on inputs ('Use details the person gave; do not invent them'). It does not, however, name the alternative create_document_pdf or state when a caller should pick one over the other, so it lacks true when-not 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?

Annotations only say readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=false — they establish that this writes and is non-idempotent but say nothing about what it writes. The description supplies exactly that: what gets persisted (verification record with issuer name, type, date, currency, total, explicitly no client details), the 7-day editor copy, the base64 return channel, the LuckPanda footer/QR branding, and a concrete rate limit of ~40 PDFs/hour per network.

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 paragraph, front-loaded with the output (what is returned) before side effects and limits. Every clause carries information, though the run-on return-format sentence is slightly harder to scan than a short list would be.

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 write tool with nested input and an existing output schema, this covers the gaps that matter: return shape, branding, persisted side effects, retention, and throughput limits. An agent has everything needed to call it and to anticipate its consequences.

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 `doc` and `page` including enums, defaults and validation-failure behavior. The description adds no field-level syntax or default detail beyond what the schema provides, so the 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 and resource ('Generates a PDF of a document') and enumerates the supported document kinds, so an agent knows exactly what it produces. It does not, however, name or contrast itself with the sibling create_document_link, which is the obvious alternative for the same document object.

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 when-to-use or when-not-to-use guidance and no mention of create_document_link as the alternative for callers who want a link rather than an embedded PDF. The context is inferable from the purpose, but nothing steers the agent between the two sibling creation tools.

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 cover safety (readOnly, idempotent, non-destructive, closed-world), yet the description adds real behavioral context: which fields come back, the meaning of a null rate_percent, and that dataset scope accompanies every answer. That is genuinely additive rather than a restatement of the structured hints.

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 scope, then a dense but purposeful second sentence covering outputs, the null-rate caveat, and dataset scope. Slightly packed with clause stacking, but every sentence carries information.

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, return values need not be explained, yet the description usefully flags the null rate case and dataset scope. Between annotations, full schema coverage, and output schema, an agent has enough to call this correctly; only comparative routing to sibling tools 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 description coverage is 100%, so the schema already documents type, limit (max 25, default 10) and the query format including the 2-to-8-digit rule. The description mirrors the query semantics ('words or code digits') but adds no syntax or constraint beyond the schema, so the 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 (searches) and resource (HSN codes for goods, SAC codes for services), plus the retrieval keys (product/service words or code digits). This is clearly distinguishable from siblings like calculate_gst and check_gstin, which compute or validate rather than look up codes.

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?

Scope is stated ('India only') and one important conditional is explained (rate_percent null means the rate was not checked against the notification, so check it). However, there is no explicit guidance on when to choose this over siblings such as calculate_gst for rate computation, leaving usage only implied.

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 openWorld=false, so the trailing 'Read-only' is largely repetition. The description does add useful scope about the breadth of returned rule content, but since an output schema exists, that content detail is mostly redundant and adds little behavioral context beyond what structured fields supply.

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 opens with the core purpose before listing return contents, so the key information leads. It is dense with enumerated clauses, though each clause is substantive rather than 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, read-only lookup with a full output schema and complete annotation coverage, the description is nearly sufficient: it conveys purpose, scope of returned rules and safety profile. The remaining gap is routing guidance relative to the calculation and check_gstin siblings, which is not addressed.

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 both parameters are fully documented (country as ISO alpha-2 with examples, document_type as a five-value enum). The description only restates 'a given type and country' without adding format or constraint detail, so the 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 and resource: it 'returns what to collect before creating a document of a given type and country', enumerating the concrete outputs (required/recommended/optional fields, tax ID and names, country invoicing rules, CGST/SGST vs IGST split, credit-note reasons). This clearly separates it from calculation siblings like calculate_gst and calculate_vat, which compute amounts rather than surface schema/rules metadata.

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 'what to collect before creating a document' implies the usage context: call this prior to document creation to discover the required inputs. However, it never names an explicit alternative or a when-not-to-use condition, despite siblings such as create_document_pdf, calculate_gst and check_gstin that an agent could 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?

Annotations already declare readOnlyHint=true, idempotentHint=true, openWorldHint=false and destructiveHint=false, so the trailing 'Read-only' is largely redundant. The description does add genuine context about the scope of the corpus (document generators plus country/trade templates and calculator pages), but says nothing about result volume, ordering, or pagination behavior.

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 opening sentence establishes the corpus, then a compact filter line. Front-loaded and free of filler, though the parenthetical inventory of generator types is somewhat long for the value it adds.

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 format need not be explained, and the description covers the domain scope. For a zero-required-parameter listing tool this is nearly complete; only result-size/ordering behavior is 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 description coverage is 100%, so the baseline is 3. The description merely restates the three filter names, adding no syntax, defaults, or combination semantics beyond what the schema already documents (including the enum and the ISO alpha-2 note).

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 ('Lists') plus the exact resource: document pages on luckpanda.app (enumerating the generator categories) and its calculator pages. This clearly separates it from the sibling calculate_*/create_* tools, which compute values or produce artifacts rather than enumerate pages.

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 this is a discovery/browse tool and notes that all filters are optional, but it never says when to reach for it over siblings like calculate_gst or find_hsn_code, nor any exclusions. Usage must be inferred from the enumerated content.

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