AI Citizenship

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, yet the description adds substantial context: the study guide is the authority, no correction via current events, no invented questions, no personal data collection, the unofficial/disclaimer status, unvetted additions must be labelled, and multi-version tests must not be assumed. These are meaningful behavioral and compliance traits beyond the structured hints.

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

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

Purpose and return values are front-loaded, and the six numbered rules are individually meaningful rather than filler. The list is long and slightly repetitive (rule 2 overlaps with rule 5), but each sentence earns its place given the compliance sensitivity.

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 fully: correctness, correct option, vetted explanation, guide page, disclaimer, and version note. It also supplies the authoritative-source and privacy constraints an agent needs to respond correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so each parameter already carries its own documentation (lang default and source, choice letter, country code, question_ref origin). The description adds only the reinforcement that question_ref must come from get_practice_questions; 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: checking the person's answer to one question from get_practice_questions. It also enumerates what is returned (correctness, correct option, vetted explanation, study-guide page), which makes it unmistakable against siblings like get_practice_questions or list_tests.

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 constrains input to a question_ref returned by get_practice_questions, establishing the prerequisite chain. It does not spell out an explicit when-not-to-use or compare against alternatives beyond that one constraint, so it falls just short of a 5.

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 read-only, idempotent, non-destructive, non-open-world behavior, so the safety profile is covered. The description adds meaningful context beyond that: the free-tier limitation, the subscription paywall in the app, the ban on quoting prices, the requirement to surface the returned disclaimer, and the warning about multiple test versions per country. It never says what the returned link itself looks like, which keeps it out of the top band.

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, but roughly 150 of the words are a six-item rules block of connector-wide compliance boilerplate that is not specific to fetching a link. For a two-parameter, single-URL tool this is oversized and a large share of the text does not earn its place against this tool's job.

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?

Purpose and parameters are adequately covered for a simple link fetch, but there is no output schema and the description never characterizes the return value beyond a passing reference to a disclaimer returned with the result. An agent knows the ethics rules but not the shape of what comes 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 100%, so both lang and country are already documented with pattern, length and provenance from list_tests. The description adds no syntax or format detail beyond the schema, so the baseline 3 applies.

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

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

The opening sentence states a specific verb and resource: retrieve the link to the AI Citizenship app for full practice. It is distinguishable from siblings like get_practice_questions because it explains the connector only exposes 8 free questions per topic while the full bank lives in the app, implying this tool serves the upsell path.

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 rather than stated: an agent must infer that this tool is for when the user wants more than the 8 free questions or the timed exam. There is no explicit 'use this when X, use get_practice_questions when Y' routing, and the numbered rules are conduct constraints, not tool-selection 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 cover the safety profile (readOnly, non-destructive, not idempotent), but the description adds substantial behavioral context annotations cannot: the exact output shape, that the answer/explanation are deliberately withheld, idempotency implications ('up to 8', optional topic), and a multi-rule usage contract (study guide authority, no PII, disclaimer, version ambiguity). This far exceeds the bar set by simple read-only hints.

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

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

Front-loaded purpose is strong, but the six numbered rules make the description long and partly repetitive (rules 1, 2, and 5 all restate 'only use vetted leak questions'). Content is valuable but a more compact phrasing would retain all guidance. Appropriate size for a tool with compliance constraints, but not tight.

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, so the description must carry return-value info — and it does (question_ref, lettered options, withheld answer/explanation). It also covers the critical flow with check_answer, disclaimer obligations, and version ambiguity. Complete for what an agent needs to call and use this tool 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 100%, so baseline is 3. The description adds cross-parameter meaning beyond the schema: the 'chosen language' ties lang to list_tests languages, 'optionally for one topic' clarifies topic is a filter, and the 1-8 bound echoes count's maximum. But it doesn't explain the country/lang relationship further. Marginal uplift over the schema alone.

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 + scope ('Get up to 8 free multiple-choice practice questions for a country's citizenship test') and clarifies what comes back (question_ref, lettered options) and what does NOT come back (answer, explanation). Distinguishable from check_answer, list_tests, get_topic_summary 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 names the next step ('after the person answers, call check_answer with the question_ref and their letter') and states when/how not to use it ('do not guess or hint the answer', 'never invent quiz questions'). This is when-to-use and when-not-to-use guidance with the alternative named.

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, yet the description adds substantial behavioral context: guide authority over external sources, no invented questions, a personal-data prohibition, disclaimer display, unvetted-additions labeling, and version-note handling. This is well beyond what the annotations 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?

Purpose is front-loaded in one sentence, but the six-item rules block is long and policy-heavy for a simple read-only lookup, reading more like global agent instructions than tool-specific guidance. Content is largely non-redundant, but the density is high relative to the tool's simplicity.

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?

Covers what is returned (summary plus covered guide pages) and the constraints needed to use it safely; with no output schema and full schema coverage, little else is required. The only minor gap is that it never states how to obtain valid country/topic values other than referencing list_tests.

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% and each parameter already documents its format and provenance (topic id from list_tests, two-letter country, language code). The description adds no further parameter-level detail, so the baseline 3 applies.

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

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

States a specific verb and resource: 'short study summary of one topic of a country's official study guide, with the guide pages it covers.' This is clearly distinct from the question-oriented siblings (get_practice_questions, check_answer) and the discovery tool (list_tests).

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 strong framing guidance ('present it as a summary of the guide, not a substitute') and links inputs to list_tests, but never states explicitly when to choose this tool over get_practice_questions or the practice-link tool. Context is clear without naming 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 cover the safety profile (readOnly, idempotent, non-destructive, not open-world), and the description adds substantial value on top: the data is 'as recorded by AI Citizenship' and may not reflect current rules, the disclaimer must be shown, multiple test versions may exist and must not be assumed, and no personal information may be collected. That is exactly the kind of caveat and handling context the 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?

The purpose and parameter behavior are front-loaded and efficient, but the six-item numbered rules block is long and largely policy boilerplate that is not specific to invoking this tool. It is not wasted entirely, but it dilutes the actionable content.

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?

There is no output schema, so the description carries the burden of explaining returns, and it does: it lists the fields of the list mode and the detail mode. Combined with the staleness/disclaimer caveats and version-note handling, an agent has everything needed to call and interpret this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both parameters are already documented (lang for names, country for detail). The description goes beyond that by explaining what the country parameter returns in detail mode (topic names, free and full question counts, notices), which clarifies the list-vs-detail behavioral split not visible in the schema.

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

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

The description gives a specific verb and resource ('List the citizenship tests AI Citizenship covers') and then enumerates exactly what the listing contains: country codes, test format, time limits, pass marks, languages, topics and free-question counts. That scope is clearly distinct from check_answer and get_practice_questions. It does not, however, name a sibling tool to route against, so it stops short of a 5.

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

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

It gives one concrete usage cue: 'Pass country for one country's detail (topic names, free and full question counts, notices)', which tells the agent when to use the parameter. Beyond that there is no explicit when-to-use-this-vs-alternatives guidance relative to the sibling practice tools, leaving usage to inference.

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