A.X.E.L Filing (public tools)

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

Annotations establish this is a safe, read-only, closed-world check, so the safety burden is already carried. The description adds useful domain context (overdrawn director loan is supported and produces a CT600A, currency is POUNDS), but does not state what the response contains or how ineligibility is reported.

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 tight sentences: purpose, the enumerated criteria, then the director-loan exception and currency. Front-loaded and every clause 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?

For a 12-parameter eligibility gate with an output schema absent, the description gives the agent enough domain context to interpret inputs and the special loan case. It falls short of describing the verdict/response shape, which is the one remaining 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 description coverage is only 8%, so the description must compensate, and it does explain the eligibility-relevant inputs: micro-entity limits, single UK trade, dormancy implied by limits, and the overdrawn loan/director-loan edge case. It does not map each of the 12 parameters to semantics, but covers the core business meaning well.

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 precise verb and resource: checks whether a company fits CT600 micro-entity eligibility, and enumerates the conditions (micro-entity limits, single UK trade, no groups/R&D/gains/property). Clearly distinct from sibling compute_ct600 (which computes) and ct600_filing_guide (which guides).

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?

Implied usage as a pre-flight gate before compute_ct600, but the description never explicitly says 'use this before filing' or names alternatives. An agent must infer the ordering from the sibling names alone.

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 establish readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context beyond the annotations: the tool is stateless and persists nothing, and it names the outputs it produces. It does not, however, mention any input-validation behavior or error conditions.

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: verb and resource first, then the stateless caveat, then a compact colon-list of outputs. Zero filler and nothing that needs to be read twice.

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 enumerates what the tool returns (tax due, taxable profit, marginal relief, losses, CT600 box values), and the stateless note answers the main caller concern. The deep nested input schema is fully documented on its own, so the remaining gap is only the absence of any routing guidance to sibling tools.

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 'figures' object carries extensive per-field documentation (e.g. taxAlreadyPaid, fullExpensing, tradingStartDate), so the schema does the heavy lifting. The description adds nothing about individual parameters, which is the correct baseline of 3 when coverage is complete.

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 (corporation tax position), and enumerates the concrete outputs (tax due, taxable profit, marginal relief, losses, CT600 box values). This clearly separates it from siblings like ct600_filing_guide and check_ct600_eligibility, which are advisory rather than computational.

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 parenthetical '(stateless, nothing stored)' implies it is safe to call freely and repeatedly, but the description never states when to reach for this tool versus siblings such as check_ct600_eligibility or ct600_filing_guide, nor any prerequisites. Usage is 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 establish readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered. The description adds little behavioral context beyond confirming it takes no arguments (already in the schema) and that it is explanatory content, with no side effects or return-format detail.

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 imperative 'READ THIS FIRST' is front-loaded as the single most important cue, followed by one efficient sentence that enumerates the guide's contents with zero filler. 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?

For a no-parameter, read-only documentation tool with annotations covering safety, the description is nearly complete: it explains the guide's scope and that no arguments are needed. Only a brief note on the form of the returned text would make it fully self-contained.

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 has zero parameters, so the baseline is 4. 'Takes no arguments' explicitly reinforces the empty schema, which is a small but helpful clarification for an agent.

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 resource (a CT600 preparation guide for this server) and enumerates its contents: qualification, figure-gathering order, terminology, and accountant referral cases. It clearly positions itself as reference material rather than a computational tool, though it never names a sibling, so sibling differentiation is only implied by 'READ THIS FIRST'.

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?

'READ THIS FIRST' gives explicit ordering guidance for when to invoke it relative to the sibling tools, and the referral-to-accountant note indicates when to stop using the server's automated path. It does not, however, name which sibling handles eligibility versus computation.

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?

Beyond the readOnlyHint/non-destructive annotations, it discloses substantive traits: no persistence or filing side effects, use of the same engine as HMRC-matched returns, an explicit prohibition on requesting a UTR or NI number, and refusal semantics for edge cases. These are non-obvious constraints an agent must honour.

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 and scope are front-loaded in the first clause, followed by the computation list and the safety constraints. It is dense but each sentence carries information; only the HMRC-engine credibility claim is somewhat expendable.

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 10-parameter, nested-object tool with no output schema, the description is strong on inputs, scope, and side effects, but says nothing about the shape of the returned estimate (line items, totals, breakdown). An agent knows what it must supply but not what it will get back.

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 80%, so most parameters are already documented in the schema, including currency, region enum meaning, and eligibility refusal behaviour; the description largely restates these. It reinforces context (one personal tax year, all in pounds) but adds little parameter-level detail beyond what the schema provides.

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 (Estimate), a specific resource (one person's UK Self Assessment), and a bounded scope (one tax year, 2025-26 or 2026-27), then enumerates exactly what is computed: income tax on salary/dividends/self-employment/interest, Class 4, student loans, payments on account, Class 1 NI. This clearly separates it from the CT600/corporation-tax siblings.

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 when this applies (personal self-assessment for one individual, one tax year) and a strong behavioural boundary: 'An estimate only: nothing is saved or filed.' It also routes out-of-scope cases (partnership, capital gains, foreign income, etc.) elsewhere, though it doesn't explicitly name a sibling tool as the alternative for those referrals.

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, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description usefully identifies the backing source (Companies House, consistent with the open-world hint) but omits any error behavior (e.g. company not found) or mention of rate limits/registration requirements for the external API.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence that leads with the verb and resource and then lists outputs; nothing is padded. The trailing phrase 'quick fit check' is undefined jargon that slightly undercuts precision.

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 carries the return-value burden and does enumerate several fields (name, status, registered office, next accounts period). However, 'quick fit check' is never explained and no failure mode or lookup limits are described, leaving gaps for a one-parameter external lookup 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 description coverage is 0% for the single companyNumber parameter, so the description must carry it. Saying 'by company number' does clarify that the identifier is a company number rather than a name, but gives no format guidance (e.g. 8-digit numeric string) or validation expectations.

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 (look up), resource (UK company), source (Companies House), and key selector (company number), then enumerates the returned fields. It is clearly distinct from the CT600/self-assessment siblings, though it never names them explicitly.

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

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

The only usage signal is the implicit 'by company number' selector plus an undefined 'quick fit check'. There is no statement of when to reach for this tool versus the sibling tax tools, and no prerequisites or exclusions.

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 this is a safe, closed-world read, so the bar is lower. The description still adds real behavioral value: it explains the two output modes (amount owed vs. full penalty schedule), the ISO date format, that filedOn defaults to today, and the domain rules that drive doubling and tax-geared penalties.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with what the tool returns and followed by the workflow dependency and format notes. Every clause carries information; nothing is filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description does explain the return shape (amount owed plus the penalty date schedule) and the input format conventions. For a six-parameter calculation tool, this is nearly complete, though it does not clarify jurisdiction scope beyond UK or what happens when a deadline is not provided.

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, including the pounds/currency for unpaidTax and the doubling semantics for accountsLateLastYear and ct600ThirdLateInARow. The description restates the ISO format and the filedOn default, adding little beyond the schema, 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?

States a specific resource (late filing penalties for UK accounts and CT600) and a specific computed output: the amount owed for a given filing date plus the full schedule of penalty dates. It also names the complementary sibling tool, so an agent can separate it from lookup_uk_company or ct600_filing_guide.

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 context: use it together with lookup_uk_company, which supplies the accounts deadline. This establishes the workflow and preconditions, but it does not state when not to use it (e.g. for non-UK entities or for self-assessment deadlines), so it stops short of full routing 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?

Adds rich context beyond the readOnlyHint/destructiveHint annotations: it discloses out-of-scope refusals (eligibility), that associated companies share CT limits and connected companies share one Employment Allowance, that dividends are taxed in the year paid, and the explicit 'never ask for UTR/NI number' rule. The annotations only carry safety; the description carries the real behavioral burden.

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 in the first clause, and the density is justified by a 6-parameter tool with deeply nested, complex schema. It is a wall of text with heavy parentheticals, which slightly hurts scanability, but most sentences carry non-redundant 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?

Given the tool's very high complexity plus an output schema that covers return values, the description still deliberately covers the tricky cases: multi-company associated/connected treatment, NI aggregation via businessInAssociation, what-if iteration, and eligibility refusals. An agent has enough 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 coverage is high (83%), so the schema already documents most fields, but the description adds genuine interpretation: dividends must carry their PAID date (taxed in that year), staffCosts must include employer NI in what-ifs so CT reflects it, and filingId/useProfile require a signed-in account. This exceeds the baseline-3 high-coverage case.

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: it delivers the director's whole year, combining the company's corporation tax AND the director's Self Assessment side by side. This is clearly distinguishable from siblings like compute_ct600 (company only) and estimate_uk_self_assessment (personal only).

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 concrete when-to-use guidance: pass filingId OR figures, call once per scenario for what-ifs, and use `companies`/`useProfile` with more than one company. It stops short of explicitly naming the sibling tools it displaces, so the agent must infer the routing from the combined-scope framing.

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