groTAX by Grovisor

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

Annotations already declare readOnly/idempotent/non-destructive for this pure computation, so the safety profile is covered. The description adds genuine domain behavior beyond that: the SBR eligibility boundaries (revenue ≤ AED 3m, periods ending by 31 Dec 2029) and the material consequence that a tax loss and disallowed interest are forfeited in an SBR year.

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 sentences, front-loaded with purpose, then the carry-forward consequence, then the input contract. No filler; each sentence carries distinct 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?

For a 32-parameter comparison tool with full schema coverage and no output schema, the description tells the agent what it computes and what it returns (tax payable and carry-forward each way). The absence of output schema is compensated by naming the outputs, though edge behaviors (e.g. what happens if ineligible for SBR) are left implicit.

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 already documents all 32 parameters (baseline 3). The description adds one important semantic that the schema does not: sbrElect is ignored by this tool, which an agent would otherwise reasonably set given the SBR framing.

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 (Compute) and resource (the same facts with and without Small Business Relief), and explicitly frames the tool as a two-way comparison of tax payable and carry-forwards. This distinguishes it cleanly from sibling grotax_compute_ct, which it names.

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?

Establishes the context by tying itself to grotax_compute_ct ('takes the same inputs'), implying it is the tool to use when a side-by-side SBR comparison is wanted rather than a single computation. It does not spell out an explicit 'use this instead when...' rule, but the routing is inferable.

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 a safe, read-only, idempotent, non-destructive operation, so that burden is lifted. The description adds valuable context beyond annotations: it discloses the output format ('markdown table plus structured rows') and the important caveat 'Indicative, not tax advice.'

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 purpose is front-loaded and the dense tax-rule summary is appropriate for a 32-parameter computation tool. It is compact but not terse; every clause contributes a rule, required input, or output note.

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?

Given the high complexity (32 parameters) and absence of an output schema, the description does well: it specifies the required parameter, optional SBR input, key computation rules, return format, and a disclaimer. Some parameter-level nuance is left to the schema, which is fully documented.

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 fully documents all 32 parameters. The description still adds meaning by explaining how some inputs drive the computation (e.g., 50% entertainment add-back, revenue drives SBR, WHT/FTC credits), going beyond bare parameter labels.

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: 'Estimate UAE Corporate Tax' and names the underlying computation method. This clearly separates it from sibling tools like grotax_get_rules or grotax_compare_sbr, though it does not explicitly call out those alternatives.

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 limited usage guidance by noting 'Only accountingProfit is required; pass revenue to test SBR.' However, it does not state when to prefer this tool over siblings such as grotax_compare_sbr or grotax_penalties, leaving the broader routing decision 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?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds genuinely useful context beyond the annotations by disclosing that each entry carries a legal source and a 'verify: true' flag indicating unverified values, which tells the agent the data is not uniformly trustworthy.

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 sentence, front-loaded with the action and scope, with the return-relevant detail (legal source, verification flag) appended efficiently. 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?

No output schema exists, so the description must carry the return-value burden, and it does partially by naming legal source and the verify flag. What remains underspecified is the scope of 'every rule' relative to the tp_thresholds sibling and the overall output shape.

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 tool takes zero parameters, so the baseline of 4 applies. With no arguments to misinterpret, there is nothing further the description needs to add here.

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+resource (list every rate and threshold groTAX uses) and disambiguates the vague tool name 'get_rules' into a concrete catalog of rates/thresholds with legal sources. It does not, however, differentiate itself from the sibling grotax_tp_thresholds, which also concerns thresholds.

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: call this to enumerate the full rate/threshold catalog when you need legal sourcing or verification status. There is no explicit when-to-use, when-not-to-use, or pointer to the overlapping tp_thresholds sibling, leaving the agent to infer the boundary.

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 (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds two behavioral facts: partial answers are tolerated and results come back ranked High → Low, which is real value in the absence of an output schema. It still says nothing about how scoring or ranking is derived, so it is useful but not rich.

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 action, followed by the prerequisite and the return-shape note; every clause is functional. The long parenthetical domain list is dense but each item maps to real checklist coverage rather than filler, so the size is defensible though slightly heavy.

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 1-parameter, deeply nested tool with no output schema, the description supplies the prerequisite call, the partial-answer allowance and the returned ordering, which is most of what an agent needs. It stops short of describing the finding structure or severity semantics, a minor gap given the otherwise complete input documentation.

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 all 18 nested answer fields carry their own descriptions and allowed values, so the schema does the heavy lifting and the baseline is 3. The description only adds the routing instruction to fetch keys/allowed values from grotax_list_health_questions, which is meta-guidance rather than new per-parameter meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run the Grovisor CT reviewer red-flag checklist') and enumerates the exact domains covered (SBR, free zone/QFZP, TP disclosure, interest cap, loss continuity, etc.), so an agent knows precisely what this tool evaluates. It also distinguishes itself from the sibling grotax_list_health_questions by assigning them different roles (input discovery vs. review execution).

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 explicit operational guidance: 'Pass the answers you know' signals partial input is acceptable, and 'call grotax_list_health_questions first for the keys and allowed values' establishes a concrete call ordering with a named alternative. Nothing about when to invoke this vs. a sibling is left 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 declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds value by disclosing the return content (answer keys, allowed values, dependsOn relationships), which matters because there is no output schema, though it stops short of describing format or 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?

One dense sentence covering subject and payload followed by a one-clause routing instruction; every clause earns its place and the purpose is front-loaded.

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 parameters and no output schema, the description carries the burden of describing returns and does so reasonably (keys, allowed values, dependsOn). Minor gaps remain around result shape and ordering, but nothing essential to calling it 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?

The tool takes zero parameters, so per the rubric the baseline is 4; there is nothing for the description to disambiguate and it makes no misleading parameter claims.

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 ('List') plus resource ('groTAX health-check questions') and enumerates the payload (answer keys, allowed values, dependsOn), which no sibling tool offers. An agent can distinguish this from grotax_health_check or grotax_get_rules without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly states when to use it relative to a named sibling: 'Use before grotax_health_check.' That is actionable sequencing guidance, though it does not state any exclusions or alternative paths for retrieving the same data.

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

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint=false, and destructiveHint=false, so safety is covered. The description adds useful behavioral context beyond annotations: penalty escalation, waiver condition, and default date behavior. It does not describe output shape or calculation assumptions, but it is strong overall.

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 dense sentences pack the due-date rule, penalty rates, waiver condition, and defaults with no filler. It is front-loaded, but the long clause chain could be easier to scan if structured as a list.

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 9-parameter calculator with no output schema, the description covers the return due date, late filing/payment penalties, late registration penalty, waiver, and date defaults. It omits explicit output fields and assumption notes, but is largely complete 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?

Schema description coverage is 100%, so the baseline is 3. The description adds meaning by linking parameters to the calculation: due date is 9 months after periodEnd, the registration waiver depends on firstReturnFiled, and blank filing/payment dates default to today/filingDate. Some of this repeats schema descriptions, but it still enriches parameter semantics.

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 title and description state that the tool returns CT return/payment due dates and estimated penalties, with specific penalty amounts and rates. It is clear what the tool calculates, but it does not explicitly distinguish itself from siblings such as grotax_compute_ct.

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 alternatives mentioned, and no exclusions. The description only provides domain rules and defaults, leaving the agent to infer when this tool is appropriate.

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, so the safety profile is covered. The description adds genuinely useful behavior context beyond that: the failure outcome (loss of Qualifying Free Zone Person status for the period plus the next 4 periods) and the regulatory basis, which is exactly the kind of consequence an agent cannot infer from 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?

Two tight sentences: the test criteria first, then the consequence. No filler, no restatement of the name, and the numeric threshold is front-loaded where an agent will read it.

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-number, read-only calculation the description covers the rule, the regulatory source, and the failure consequence. With no output schema present it could optionally say what the result contains (pass/fail, headroom), but nothing needed to invoke it 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 100% with both parameters documented, including the nuance that nonQualifyingRevenue excludes disregarded revenue. The description adds no further parameter semantics, so the baseline of 3 is appropriate when the schema does the heavy lifting.

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 (test) and resource (free zone company's non-qualifying revenue against the de minimis limit), with the exact rule stated (lower of 5% of total revenue or AED 5m, MD 229 of 2025). No sibling tool overlaps this domain, so an agent can select it unambiguously.

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 makes the triggering condition clear (a QFZP's non-qualifying revenue) and states the consequence of failure, which implicitly tells the agent when this test matters. It does not name any alternative tool or state when not to run it, but the siblings are unrelated domains so the gap is minor.

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, destructiveHint=false, and openWorldHint=false. The description adds substantive domain behavior by spelling out the exact threshold rules (e.g., > AED 40m with a category > AED 4m triggers the TP Disclosure Form). It does not describe return format or handling of missing optional parameters, but it meaningfully extends the safety profile with evaluation logic.

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 sentence front-loads the core action ('Check which UAE transfer pricing documents apply') and then efficiently enumerates the conditions. Every clause carries necessary threshold information with 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?

The description gives the governing rules and all five parameters are schema-documented, but there is no output schema and the description does not state what the tool returns (e.g., a list of applicable documents) or how it behaves when optional inputs are omitted. For a check tool with zero required parameters, that gap keeps completeness at a minimum viable level.

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 each parameter's meaning. The description nevertheless adds value by mapping those parameters to decision thresholds (revenue > AED 200m, relatedPartyTotal > AED 40m, connectedPersonPayments > AED 0.5m, etc.), giving rule-level semantics beyond the raw field definitions.

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 specific verb ('Check which UAE transfer pricing documents apply') and resource (UAE TP documents), and even enumerates the thresholds for each document. It is highly specific, but it does not explicitly differentiate itself from any sibling tool (though no sibling appears to be a near-equivalent).

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: call this tool when you need to determine which UAE transfer pricing documentation obligations apply. There is no explicit 'use when' clause, no exclusions, and no named alternative among the siblings, so guidance remains at the implied level.

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