Spain Legal by Legal Fournier

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

Annotations already declare readOnly, idempotent, non-destructive, non-openWorld behavior, so the safety profile is covered. The description adds genuinely new behavioral context by labeling the operation 'qualitative gatechecks' and disclosing the response shape (rule trace, review level, resources), which tells the agent this is a screening advisory rather than a definitive ruling.

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 with no filler; the verb and domain come first and the output disclosure follows. It is efficiently sized, though the trailing 'canonical MCP resources for follow-up' clause is borderline boilerplate.

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. However, for a 14-parameter tax-regime screening tool the description is thin: it does not explain how the many boolean gate flags interact, that some inputs are deprecated, or what 'review level' implies for the caller's next step.

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 79%, so the schema already carries most parameter meaning (including the deprecated note on years_since_last_spanish_residency). The description adds no parameter-level detail at all, so 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 states a specific verb and resource ('Screen Spain's Beckham regime') and adds the mechanism ('qualitative gatechecks') plus the outputs (rule trace, review level, canonical MCP resources). It is clearly distinct from siblings like compare_tax_regimes or get_residency_path, though it never names an alternative.

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 only implied: the phrase 'for follow-up' hints this is a first-pass screening step in a workflow, but there is no explicit when-to-use, when-not-to-use, or comparison against sibling tools such as compare_tax_regimes. An agent must infer the routing itself.

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 genuine value beyond that by disclosing the return character — reasoning plus a review level plus MCP resources, explicitly not rate tables — which tells the agent this is advisory/conceptual, not an authoritative rate calculation.

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 with no waste, front-loaded with the verb and resource, then the output modality. Nothing is padding.

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 re-explained, and 0 required parameters lowers the burden. The description still conveys the nature of the output (reasoning/review level/resources) and that it is conceptual. The only gap is the lack of routing guidance among the many legal siblings.

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%, including a rich nested beckham_assessment object with per-field descriptions and a deprecated-field note. The description contributes no parameter-level detail, so the baseline 3 is appropriate – the schema carries the 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?

States a specific verb (compare) and resource (Beckham vs standard Spanish resident taxation) and, crucially, clarifies the output modality: 'conceptually, returning reasoning, review level, and canonical MCP resources instead of rate tables.' This implicitly separates it from check_beckham_eligibility and rate-table tools. It stops short of a 5 because it never names the sibling tool it differs from.

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 word 'conceptually' and by the contrast with rate tables, but there is no explicit when-to-use, no when-not, and no routing to alternatives such as check_beckham_eligibility for a straight eligibility check. The agent must infer the scenario (regime-choice reasoning vs eligibility assessment).

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=false and openWorldHint=true, and the description adds real value beyond them by labeling the call 'consequential' and requiring explicit user consent twice. It does not discuss retry/idempotency behavior or what happens on duplicate submission, which is relevant given idempotentHint=false, but the consent framing is substantive.

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, both front-loaded: the action first, the safety condition second. Nothing is redundant 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?

For a 21-parameter mutation tool with a rich schema, full coverage, and an output schema, the description covers purpose and the critical consent gate. It could say more about how the accepted lead is processed downstream or idempotency handling, but nothing essential to a correct call 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 all 21 parameters are already documented in structured form and the baseline of 3 applies. The description adds no field-level guidance (e.g. how legal_area or risk_flags should be populated) beyond reinforcing the consent booleans.

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 and resource ('Create an accepted Legal Fournier lead from an agent workflow'), which is unambiguous and clearly a write/lead-creation operation. It does not name sibling tools it should be preferred over (e.g. route_to_legal_fournier_help, run_legal_fournier_tool), so sibling differentiation is left to the schema reference.

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?

'call only when the user has asked to contact Legal Fournier and has consented to follow-up' gives an explicit gating condition for invocation. It stops short of naming the alternative path (route_to_legal_fournier_help) as a prerequisite step, but the when-to-call condition is clear rather than 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 readOnly, idempotent, non-destructive, and closed-world. The description repeats output content but adds no behavioral context such as auth requirements, rate limits, or side effects. With an output schema present, return value details are redundant.

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?

Single sentence, front-loaded with the action and returned items. Minor jargon but 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?

For a no-param read-only tool with an output schema and full annotations, the description adequately states what it returns. It lacks usage context, but that is covered in another dimension.

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?

Zero parameters, so baseline is 4. The description need not address parameters, and the schema is empty.

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 'Return' and specific resources 'NIE and TIE workflow' and 'canonical process resource'. Distinguishes from siblings by focusing on process explanation, though it doesn't name alternative 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?

No explicit when-to-use, when-not, or alternative tools. The only hint is 'for agents', which is not actionable usage 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 cover the safety profile (readOnly, idempotent, non-destructive, closed-world). The description adds genuinely new behavior: long content is paginated, video metadata is not a reviewed transcript, and retrieved text is untrusted reference material rather than agent instructions — a prompt-injection warning that annotations cannot express. The 'never fetches caller URLs' clause is consistent with openWorldHint=false.

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?

Four short sentences, front-loaded with the core purpose, then the video caveat, pagination, and trust model. Every sentence adds distinct, actionable information with no restatement of the name or annotations.

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-value explanation is unnecessary, and annotations carry the safety profile. The trust model and pagination are covered, but the id/uri relationship and pagination parameter units remain undocumented for a tool whose schema is 0% described.

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% across four parameters, so the description must compensate. It gives the addressing alternative (id or uri) and implies pagination controls (offset/max_chars) via 'Long content is paginated', but does not state that id and uri are mutually exclusive, nor what units offset/max_chars use. Partial compensation, not full.

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 (fetch) plus the resource types (published article, video metadata, canonical resource) and the addressing mode (stable id or uri), which implicitly contrasts with the sibling 'search' that must discover identity first. It does not explicitly name a sibling tool, so it stops short of the top score.

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 'by stable id or uri' (you must already know the identifier) and a negative constraint ('caller-supplied URLs are never fetched'), but there is no explicit when-to-use/when-not guidance or named alternative such as 'search'. The agent must infer that this is the retrieval step after discovery.

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, so the safety profile is covered. The description adds that matching spans 'public tool page and MCP workflow', but says nothing about ranking behavior, escalation, pagination, or limits (e.g., max_results interaction).

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?

It is a single front-loaded sentence with no wasted words. Given the tool's six parameters and routing complexity, it is arguably a touch thin, but it is efficiently 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?

An output schema exists, so return values need not be explained, and the schema covers parameters. Still, for a router tool sitting among overlapping siblings, the description lacks the disambiguation an agent needs to pick it over route_to_legal_fournier_help or run_legal_fournier_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 100%, so all six parameters (query, area, max_results, include_all_tools, complexity_signals, preferred_language) are documented in the schema. The description adds no format or syntax detail beyond what the schema already 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?

The description names a specific verb ('Match') and resource (a Spain legal/tax/property/business/private-client case) and the target (best public tool page and MCP workflow). It's clear what the tool does. However, it does not distinguish itself from the sibling route_to_legal_fournier_help or run_legal_fournier_tool, which sound like adjacent routing 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 when-to-use or when-not-to-use guidance, and no alternatives are named despite several routing-related siblings. Usage is only weakly implied by the phrase 'Match a ... case to the best ... tool page'.

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=true, so the safety profile is covered. The description usefully reinforces this with an explicit list of side effects it will not produce (no quote, booking, order, payment) and notes the data is 'live', adding specificity beyond the hints, though it says nothing about result shape or limits on the window.

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 zero filler; the affirmative purpose is front-loaded and the critical non-mutation caveat follows immediately. 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?

With an output schema present, return values need not be explained, and annotations cover safety. Purpose, scope, and the no-side-effects constraint are all stated. Minor gaps remain: no mention of constraints on window size, rate limits, or what a caller does with the slots returned.

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 three required fields (from, to, timezone) are documented with ISO 8601 and IANA format guidance. The description adds no parameter-level detail, so the baseline 3 is appropriate when the schema carries the full burden.

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 (Read) plus resource (live Cal.com availability) and pins down the exact offering (45-minute agent-paid Legal Fournier consultation). An agent can distinguish this from get_paid_consultation_options or check_beckham_eligibility without opening any 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?

The negative scoping ('never creates a quote, booking, order, or payment') tells the agent what this tool will not do, which implicitly frames it as a pre-booking lookup. However, no sibling is named and there is no explicit when-to-use trigger or ordering guidance relative to get_paid_consultation_options or the booking/contact 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 declare readOnly, idempotent, non-destructive, openWorld. The description adds genuinely useful behavior: the return payload contains live prices, fulfillment terms, request schemas, quote endpoints, and payment endpoints, and it requires explicit user authorization before any downstream action. That is real added context beyond the annotation flags.

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 payload contents, then the read-only boundary. Every sentence carries distinct information with no filler, though it is slightly dense in enumerating return fields.

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

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

With an output schema present and zero input parameters, the description's job is mostly scoping and intent, both of which are covered: what the tool does, what it returns, and what it deliberately does not do. An agent has everything needed to call 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?

There are zero input parameters, so there is nothing for the description to disambiguate. The baseline for a parameterless tool applies; the description correctly focuses on what comes back rather than inventing 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?

States a specific verb (discover/arrange) and resource (paid consultations with Legal Fournier via x402 in USDC on Base), and enumerates the two offerings (written email consultation, 45-minute call). This is clearly distinguishable from siblings like get_paid_call_availability or create_legal_fournier_contact_request.

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 frames the usage pattern: agents retrieve options here, then use the returned HTTPS endpoints 'after explicit user authorization' to actually submit or book. It also sets a clear boundary ('never creates an order or submits payment itself'). It stops short of naming the alternative sibling tools directly, so it is clear context without explicit routing.

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 genuine behavioral context beyond them: it discloses that the output carries 'explicit caution flags for counting issues,' signalling the agent will receive warnings about continuity/absence problems rather than a bare timeline.

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 sentence that front-loads the action, the domain, the required inputs, and the caution-flag behavior with zero filler. Nothing is repeated from the title or 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?

With an output schema present, return values need not be explained, and annotations cover safety. However, for a 7-parameter tool whose optional fields drive the specificity of the answer (nationality_track, special_nationality_basis, continuity_confirmed), the description says nothing about when those matter or how this differs from sibling eligibility/visa 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 71%, so the schema already documents most inputs. The description only echoes 'current status and time in Spain' (the two required params) and adds nothing about the optional nationality_track, continuity_confirmed, or qualifying_legal_residence_years fields. 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?

Specific verb and resource: 'Explain the next permanent-residency or nationality milestone from current status and time in Spain.' An agent can tell this is a status/milestone explainer rather than a document processor. It stops short of naming which sibling it replaces (e.g., get_visa_options for pre-arrival planning), so it is clear but not sibling-differentiated.

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?

'From current status and time in Spain' implies this is for people already in Spain with an immigration status, weakly distinguishing it from the pre-arrival sibling get_visa_options. There is no explicit when-to-use, when-not-to-use, or named alternative, so 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 declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds that it ranks branches using 'evergreen logic' and emits decision traces/next actions, which is meaningful behavioral context, but it says nothing about how ranking is scoped or what disqualifies a route.

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 core action and then the outputs; there is no wasted filler. It leans on jargon ('evergreen logic', 'canonical MCP resources') that costs some readability but not length.

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, and annotations carry the safety profile. But for a 10-parameter tool with 5 enums and intent-dependent optional params, the description gives no sense of which inputs gate which routes, leaving the agent to reverse-engineer that from the schema.

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 80%, so the flat params are largely documented by the schema itself, and the 5 enums are self-describing. The description adds no parameter meaning beyond the schema and does not clarify the conditional relationship between intent, income_source, and the sponsor/investment params.

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 (Rank) and resource (Spain residence routes), and discloses outputs (decision traces, next actions, resources). However, it never distinguishes itself from overlapping siblings like get_residency_path or check_beckham_eligibility, so an agent must guess which route tool applies.

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 exclusions, and no alternatives named despite several sibling tools (get_residency_path, check_beckham_eligibility, compare_tax_regimes) that plausibly overlap. The agent is left to infer the routing condition entirely.

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, so safety is covered. The description adds useful context that the tool produces a decision and message rather than performing the escalation itself, but says nothing about permissions, rate limits, or what happens to the handoff afterward.

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 that front-loads the decision verb and enumerates the outputs. Every clause earns its place with no 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?

With an output schema present, the description need not explain return values, and annotations cover the safety profile. It is largely sufficient, though it omits whether the tool merely recommends escalation or triggers anything downstream, leaving a small gap for a routing/decision 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 100% with all five parameters (three enum-constrained) documented in the schema itself. The description adds no parameter-level detail such as how blockers or urgency affect the routing decision, so the baseline of 3 applies.

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

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

States a specific verb ('Decide whether...escalated') and resource ('Spain legal matter'), plus the three artifacts it returns (service match, preparation checklist, handoff message). This distinguishes it from siblings like create_legal_fournier_contact_request or run_legal_fournier_tool, which act rather than decide, but no sibling is named 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?

Usage is implied by the escalation framing and the presence of inputs like 'blockers' and 'already_filed', which hint at when routing is warranted. However, there is no explicit when-to-use/when-not guidance and no pointer to the alternative tools an agent should consider first.

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 closed-world, so the safety profile is fully covered elsewhere. The description adds the shape of the outcome (intake screening, missing facts, complexity flags, handoff guidance), which is genuinely useful, though much of it is also captured by the output schema.

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 sentence with no filler, and the verb-plus-resource framing is front-loaded before the return-value list. Nothing is wasted, though the sentence crams the return fields into the same breath as the action.

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 complex, nested, 8-parameter tool the description is adequate but thin: it tells the agent what comes back but not how to choose a tool_id, that different tool_ids demand different subsets of facts/numbers, or that providing complexity_signals triggers human review. The output schema covers return values, so the gap is mainly in input assembly 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 75% with 8 parameters, several deeply nested (property, digital_nomad_income), so the schema does most of the work. The description adds nothing about tool_id selection, the relationship between tool_id and the fact/number inputs, or conditional parameter requirements, but at this coverage level a 3 is the appropriate 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?

States a specific verb (run) and resource (a Legal Fournier public calculator or screener) and goes on to name what it returns. An agent can distinguish it from discovery-oriented siblings like find_legal_fournier_tool, but the description never explicitly contrasts it with outcome-specific siblings such as check_beckham_eligibility or compare_tax_regimes, which overlap with some tool_id values.

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?

"directly inside MCP" implies usage in place of driving the public web tool by hand, and the generic tool_id-driven design implies a find-then-run flow alongside find_legal_fournier_tool. However there is no explicit when-to-use, when-not-to-use, or statement of which sibling to prefer for a given legal question, leaving routing 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, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds value beyond that by disclosing that results carry source citations and, importantly, that retrieved text is untrusted reference material and never agent instructions — a prompt-injection caveat annotations cannot express.

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, each doing distinct work: scope, filters, and the untrusted-content warning. The scoping sentence is front-loaded and nothing is redundant.

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 spelled out, and the annotations cover the safety profile; the added citation and untrusted-content notes fill the remaining behavioral gap. It falls slightly short on parameter mechanics (default query behavior, result caps, enum meaning) that a 5-parameter, 0%-documented schema would benefit from.

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%, so the description carries the full parameter burden. It names three of the five filter dimensions (language, type, topic) and their purpose, but never explains query (default empty string, 500-char cap), max_results (1-20 cap), or the enum values including the 'und' language code.

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 (search) plus the resource scope (published Legal Fournier articles, YouTube videos, canonical legal resources), which an agent can act on directly. It never names a sibling such as fetch or run_legal_fournier_tool, so the boundary with those tools is left implicit rather than stated.

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 scope statement and by the security note about treating retrieved text as untrusted reference material, which is genuinely useful operational guidance. There is no explicit when-to-use/when-not clause and no routing to fetch or the domain-specific sibling tools, so the agent must infer the choice.

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