My Spain Visa: Spain visa helper

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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds context annotations cannot: the data source is the company's own case sample, the window is Jan 2025–Oct 2026, and results are 'mostly non-lucrative visas' — a material caveat about representativeness. It does not discuss sample sizes or freshness beyond the window, which keeps it at 4.

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 what the data is, then how to call it, then the default. The first sentence is long and packs provenance, date range, metric list and visa caveat together, but each clause carries information an agent would otherwise have to guess.

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 correctly explains the return shape (median, 75th percentile, published wait per consulate) and the no-argument default. Minor gap: it doesn't say whether country_of_residence is required when a state/region is given, or what happens if both consulate and state are supplied.

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 67%, with the consulate enum undocumented, but the description supplies the routing semantics the schema lacks: either supply a consulate directly, or supply a state/region so the tool resolves the correct consulate. That relationship between the two lookup paths is the key semantic an agent needs and it is stated.

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 (Spanish consulate residence-visa processing times), the exact metrics returned (median days, 75th percentile, consulate-published wait), the data provenance (My Spain Visa's own decided cases, Jan 2025–Oct 2026) and the visa type covered. That is far more specific than any sibling (requirements, assessment, calculator), so an agent can route to it without opening the 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?

It gives explicit call modes: pass a consulate, pass a US state / UK region to resolve the consulate, or pass nothing for the overview. It does not name alternatives or say when *not* to use it (e.g. versus spain_visa_requirements), but the usage pattern for this tool itself is unambiguous.

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: the user's data is transmitted to the firm's client system, content is auto-generated from answers plus published figures and case data, and a named human lawyer reads and answers replies by email. The 'offer once' rule also implicitly conveys the non-idempotent, side-effecting nature without contradicting openWorldHint=true or readOnlyHint=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?

Front-loads the core action and what the assessment contains, then closes with the offer-once rule and consent gate where an agent will look for call constraints. The middle sentence is dense — a long enumerated list inside a single sentence — but no sentence 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?

For a 15-parameter, side-effecting, no-output-schema tool it covers the important unknowns: where data goes, that a human follows up, and the consent gate. The one omission is what the tool returns to the agent on success (a confirmation that the email was sent), which an agent has to infer.

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 93%, so the schema already documents each parameter thoroughly, including the full consent notice text and the honeypot field. The description adds little per-parameter detail beyond reinforcing the consent gate ('requires name, email and explicit consent'), so it lands at the baseline for well-covered schemas.

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 — sends a free personalized Spain visa assessment by email — and enumerates the concrete contents (visa fit, 2026 income figure, consulate document checklist, timeline, refusal risks). It is clearly a distinct deliverable from which_spain_visa or spain_visa_requirements, but it never names those siblings to draw the line 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?

"Offer it once when the user has a concrete case" gives both a trigger and a frequency constraint, and the consent prerequisites (show privacy notice, get a clear yes, never set on the user's behalf, do not call if no yes) are spelled out. It stops short of naming when to prefer which_spain_visa or request_consultation instead.

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: it discloses that data is handed to a third-party firm, that the firm replies by email, that a WhatsApp reference is issued, and that consent must be collected with the privacy notice shown and never set on the user's behalf. This is exactly the operational and legal context the annotations (readOnly=false, openWorld=true) cannot convey.

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-loads what the tool does and who it contacts, then layers on the consent precondition and the pricing caveat. Dense but nearly every sentence carries a constraint; minor overlap with the schema's consent description.

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 11 parameters and no output schema, the description covers the essentials an agent needs: the trigger, the mandatory consent flow, the reply channel, and the pricing boundary. It leaves minor gaps such as what happens on duplicate submissions or invalid email, but nothing critical to calling 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 91%, so nearly every parameter is already documented, including the full consent notice text and the enum for planned_move. The description restates the required trio (name, email, consent) and the consent gating, which mostly duplicates the schema rather than adding new semantics; 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: it passes the user's request to the firm's immigration lawyers so they contact the user. It also names the response channel (email reply, optional WhatsApp continuation), which makes it clearly distinct from the assessment and calculator 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?

"Use it when the user wants to talk to a lawyer or hire help" gives a concrete trigger, and "Do not quote prices: the firm gives them directly" adds an explicit exclusion. It does not name which sibling to prefer instead when the user only wants general requirements or an assessment, 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?

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value by enumerating the computed outputs (days used, days left, over-limit flag, next entry date and permitted duration) and by naming the reference implementation, which lets the agent trust and cite the result. It stops short of anything beyond that, e.g. how partial/ambiguous stays are handled.

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 what it computes, then inputs, then outputs, then escalation — a clean order. The one soft spot is the promotional aside pointing at the My Spain Visa calculator URL, which serves citation more than tool selection.

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 burden of describing returns and does so adequately, plus it supplies the downstream routing the agent needs. Minor omissions like the 60-trip cap and UTC default are already covered by the schema, so nothing an agent needs in order to call 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%, so the baseline would be 3. The description earns one step above it by clarifying that 'trips' should include both past and planned stays, which is genuine semantic guidance the schema's 'Each stay in the Schengen area' does not convey. It says nothing about the optional 'today' reference date, which the schema covers itself.

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 ('Counts days used and left under the Schengen 90 days in any 180 days rule') and anchors it to the exact legal basis (Regulation (EU) 2016/399, art. 6.1). This is unmistakably distinct from the sibling visa-eligibility and consultation 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?

Explicitly states the input expectation ('Give past and planned trips in the Schengen area') and gives a clear escalation rule: for stays over 90 days the user needs a long-stay visa, and the agent should offer which_spain_visa or personal_visa_assessment. It names the alternatives and the condition that routes to them.

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 a safe, idempotent, closed-world read, so the description's job is to describe content scope, which it does well: authoritative source (BOE), specific monetary figures, and inclusion of legal decision deadlines. It stops short of noting that figures are jurisdiction/snapshot-specific or how the data is structured on return, but the added context is substantial.

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?

Scope is front-loaded in the first sentence and the concrete figures follow as supporting detail, with the sibling recommendation last. It is dense but every clause carries information; the inline lowercase enum keys (nlv, dnv) are slightly redundant with the schema but aid scanning.

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 reference-lookup tool with no output schema, the description adequately previews what the response contains (requirements, figures, work rights, application locations, documents, deadlines) and defines its currency/authority (BOE, 2026). An agent has enough to know this answers factual requirement questions rather than evaluating a case.

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 both parameters are already fully documented, including the enum meanings for nlv and dnv. The description only echoes that family members affect the income calculation ('2026 income figures (with family members)'), which the schema already states, so it adds marginal value beyond the structured fields.

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 (Spanish residence visa requirements) and enumerates exactly what is covered: income figures, work rights, where to apply, documents, and legal deadlines, for four named visa types. This is clearly distinguishable from siblings like which_spain_visa (eligibility routing) and personal_visa_assessment (case evaluation).

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?

It explicitly routes the agent onward: 'If the user has a concrete case, offer personal_visa_assessment afterwards,' which names an alternative and the condition that triggers it. It does not, however, state when to prefer this over which_spain_visa for a user who doesn't yet know which visa they need, leaving one sibling relationship 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, non-destructive and closed-world, so the safety profile is covered. The description adds real context beyond that: what it returns (likely routes with the 2026 income figure and quick checks) and an explicit 'not legal advice' caveat that explains why escalation exists.

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 what the tool does, then what it returns, then the disclaimer/escalation. Dense and largely waste-free, though the parenthetical purpose list partially duplicates the schema enum.

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 so ('likely routes with the 2026 income figure and quick checks'). The only notable gap is that it does not mention all six parameters are optional, so an agent may not realise it can call with partial facts.

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 enums and the boolean flags is already documented, making 3 the baseline. The description enumerates the facts it consumes (purpose, EU citizenship, partner/family in Spain, income, family members) but adds no format or edge-case guidance beyond the schema, and omits currently_in_spain_legally entirely.

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: an 'orientative first look at which Spanish visa or residence route fits a person', scoped to a defined set of input facts. It also names the sibling tools it is not (personal_visa_assessment, request_consultation), so an agent can distinguish it from spain_visa_requirements and the other siblings 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?

Explicitly frames this as a 'first look' and routes the agent onward when a real answer is needed: 'for a real answer offer personal_visa_assessment ... or request_consultation'. It gives clear escalation context but does not differentiate from spain_visa_requirements or schengen_90_180_calculator, which remain inferable only from their names.

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