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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: it searches only active 412.x laws and, crucially, falls back automatically to all legal areas with a hint in the message field when no hits occur.

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 XML-style tags (use_case, important_notes, example) front-load the routing decision and fallback behavior efficiently. Content is tight, though the tag scaffolding is slightly heavier than a plain sentence would need.

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. The description still covers fallback behavior, cross-tool routing, and a synergy note (swiss-courts-mcp) — enough for an agent to call it correctly. Only minor gaps (limit semantics) remain.

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 single required parameter 'query' is already well documented in the schema (subjects, examples). The description repeats the 412.x scoping and adds a usage example (query='Elternrat', limit=10), but adds little semantic detail beyond the schema, and the optional 'limit' parameter is not addressed. With the schema carrying the query 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 (Sucht) plus resource (Zürcher Bildungsrecht, Ordnungsnummern 412.x), giving scope precisely. It explicitly distinguishes itself from the general sibling search_laws by contrasting the narrow 412.x-series with the full corpus.

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 <use_case> block names the alternative (openlex__zhlaw_search_laws) and the exact condition for choosing this tool (query clearly in the education domain: Schule, Lehrpersonen, Kindergarten, Sonderpädagogik, Tagesstrukturen). It also routes article-level lookups to openlex__zhlaw_search_articles, leaving nothing 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=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds valuable behavioral context beyond annotations: it specifies the return content (title, all paragraphs, full text), the failure mode (count=0 if article doesn't exist), and supported article number formats (28, 28a, 28bis). It does not mention auth or rate limits, but none are implied.

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 description is structured with clear tags (<use_case>, <important_notes>, <example>) and front-loads the core purpose. Every sentence provides useful information without redundancy, and the example at the end is brief and directly actionable.

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 simplicity, the presence of an output schema, and the annotations covering safety, the description is complete. It covers purpose, usage, prerequisites, alternatives, return behavior, error handling, format details, and an example. Nothing essential is missing for an agent 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?

The context signals schema description coverage as 0%, so the description must compensate. It provides a concrete example (law_identifier='VSG', article_number='28') and thoroughly explains article_number formatting (no 'Art.' prefix, supports 28, 28a, 28bis). However, it does not explain the law_identifier parameter's accepted formats (Ordnungsnummer vs. Abkürzung) in the description itself, leaving that to 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 states a specific verb ('Extrahiert') and resource ('einzelnen Artikel aus einem Zürcher Gesetz'), and distinguishes itself from the sibling tool openlex__zhlaw_search_articles by noting that search is for finding relevant articles first. An agent can immediately understand this is for retrieving a specific known article.

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 <use_case> block explicitly states when to use this tool (when the exact wording of a specific article is needed), the prerequisite (law and article number known), and the alternative (openlex__zhlaw_search_articles to first find relevant articles). This is comprehensive 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 read-only, idempotent, non-destructive, closed-world semantics, so the safety profile is covered. The description adds real behavioral detail beyond that: include_content=True returns full text capped at 5000 characters with truncated=True, and the recommended recovery path via get_article. It still doesn't state error behavior for unknown identifiers, which keeps it short of a 5.

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 clearly tagged sections with the primary purpose front-loaded in the first sentence. The list of important laws (VSG, LPG, PBG, StG, KV) is mildly gratuitous for an agent that passes an identifier, but overall there is little waste.

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 no explanation here. The description covers identifiers, the content-vs-metadata toggle, the truncation limit, and the fallback tool — everything needed to call this one-required-parameter 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?

Measured schema coverage is 0%, so the description must carry the parameters and largely does: it names LS numbers ('412.100') and abbreviations ('VSG') for identifier and explains what include_content=True produces. It adds meaning beyond the raw schema, though it does not enumerate every supported abbreviation the schema lists.

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 (abrufen) and resource (Zürcher Gesetz) plus the two accepted identifier forms (Ordnungsnummer or Abkürzung). It also names the sibling tools to route through when the identifier is unknown, so an agent can distinguish it from search_laws and get_law_metadata.

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 <use_case> block states the precondition explicitly (identifier already known) and names the alternatives (openlex__zhlaw_search_laws, openlex__zhlaw_find_education_laws) for the discovery path. The <important_notes> add a fallback route to get_article when content is truncated.

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/openWorld/idempotent/non-destructive, so the description's added value is the operational detail: a real HTTP request to www.zh.ch taking 1-3s, the network-access requirement, the fields returned (title, PDF links, change date, ZH-Lex URL), and explicit 404/timeout behaviour (found=False with error detail). That is rich context 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?

Tagged sections (<use_case>, <important_notes>, <example>) front-load the moment of use, then the caveats, then a concrete example. Every sentence carries information; nothing is padding despite the 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?

An output schema exists, yet the description still names the returned fields and the failure shape, which is more than required. For a single-parameter, open-world network tool, an agent has everything needed to call it correctly and interpret the result.

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 reported as 0%, so the description must carry the burden, and it largely does: it supplies an example (sr_number='412.100') and, more importantly, a constraint the schema does not encode — only Ordnungsnummern are accepted, no abbreviation lookup. It could still be clearer about format edge cases, but it meaningfully extends the bare pattern field.

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 ('Ruft aktuelle Metadaten eines Gesetzes live von zh.ch ab') and immediately distinguishes itself from every sibling by declaring it is the 'Einziges Tool mit Live-HTTP-Aufruf; alle anderen Tools lesen den lokalen Cache'. An agent can classify 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?

The <use_case> block gives concrete triggers (checking whether a law changed, which PDF version is current, which ZH-Lex URL to link) and explicitly contrasts this tool against the cache-reading alternatives. When-to-use and when-to-use-something-else are both present.

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, so safety is covered. The description adds genuine behavior beyond that: sr_prefix semantics, active_only hiding repealed laws, offset-based pagination, and a clear disclosure that the result is metadata (Titel, Abkürzung, SR-Nummer, Status) and NOT full text.

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?

Tags (use_case, important_notes, example) keep it front-loaded and skimmable, and every sentence carries routing, filter semantics, or return-shape information with no filler.

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

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

For a paginated list tool with annotations covering safety, the description supplies routing, filter semantics, pagination, and the explicit 'kein Volltext' return scope. Together with the output schema, 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?

Per the signal, schema description coverage is low, so the description must compensate. It does: it explains sr_prefix as an Ordnungsnummer prefix with real codes (412, 331, 700, 131, 810), confirms active_only semantics, and shows limit/offset usage in the example, adding meaning beyond the bare 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?

States a specific verb (auflisten) and resource (Zürcher Gesetze) with the scoping detail 'optionaler Filter nach Rechtsgebiet'. The use_case block explicitly differentiates from siblings search_laws and find_education_laws, so an agent can route 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 use_case names the exact condition to pick this tool (structured overview of all laws in a legal area) and names the two alternatives with their own selecting conditions (targeted text search, education-only). Routing is fully specified.

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), and the description adds substantial context beyond them: substring-match semantics (no FTS5), case-insensitivity, count=0 on no match, and the cache-dependency with a hint surfaced in the message field. This is rich, non-obvious behavioral disclosure.

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 purpose, then organizes usage, caveats, and an example into clearly labelled sections. Every sentence adds information; nothing is filler despite the multi-part structure.

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 described, yet it still notes count=0 behavior. Combined with the cache requirement, match semantics, and routing to the sibling tool, 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?

Schema description coverage is reported as 0%, so the description must compensate, and it does: it explains that the law is parsed into articles and that title and content are both searched, plus a concrete example (law_identifier='VSG', query='Elternrat'). It still doesn't clarify the law_identifier format (Ordnungsnummer vs. Abkürzung) beyond the example, so not a full 5.

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) and resource (all articles of a specific law) with clear scope. It explicitly distinguishes itself from the sibling openlex__zhlaw_get_article, so an agent can route correctly without opening either 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 <use_case> block states exactly when to use it (law known, article unknown) and names the alternative (openlex__zhlaw_get_article) for the case of a known article number. This is explicit when-to-use and when-to-use-something-else 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, so the safety profile is covered. The description adds genuine operational context beyond that: BM25 relevance ordering, a hard 50-result cap, cache-backed search, and a pointer to get_law_metadata for freshness. It does not describe pagination beyond the limit cap, keeping it just short of a 5.

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?

Tag-delimited sections (use_case, important_notes, example) front-load the routing decision and keep each block tight, with a concrete worked example. Slightly verbose for the amount of content, but every block carries distinct information.

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

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

With an output schema present, return payloads need not be explained, and the description still covers scope, ranking, limits, and cache-freshness caveats. Coverage is strong; only finer ranking/pagination behavior is left implicit.

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

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

The nested schema already documents every field (limit, query, sr_prefix, active_only) with examples, so the reported 0% coverage reflects the wrapper 'params' node rather than real gaps. The description reinforces sr_prefix examples (adding 700=Bau) and the limit cap, but largely restates schema content, warranting the baseline 3.

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 ('Volltextsuche in allen Zürcher Gesetzen') plus the retrieval mechanism (FTS5-Ranking). It explicitly distinguishes itself from siblings openlex__zhlaw_find_education_laws and openlex__zhlaw_search_articles by scope, so an agent can route 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 <use_case> block states exactly when to pick this tool ('wenn das Rechtsgebiet unbekannt ist') and names two alternatives with the conditions that favor each (Bildungsrecht 412.x, articles within a known law). Nothing is left to inference.

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

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

Annotations already declare write (readOnlyHint=false), openWorld, idempotent and non-destructive. The description adds substantial context beyond that: ~970 laws downloaded from HuggingFace, ~25s first run, specific SQLite/FTS5 target, internet requirement, and a critical caveat that the dataset is frozen (newest version dated 2023-01-01) so this tool does NOT make law texts more current. That last point is high-value behavioral disclosure no annotation could carry.

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 use_case / important_notes / example tagging is well front-loaded and each block earns its place. It is on the long side, but the length is justified by the frozen-dataset warning; only minor tightening is possible.

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 annotations cover the safety profile. Combined with runtime, source, duration, network requirement, cache-freshness behavior and the data-staleness caveat, an agent has everything needed to decide and invoke 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 0% and there is one parameter, so the description must carry the semantics — and it does: force=False skips download when the cache is <24h old and returns status='cache_fresh', force=True forces a re-download, with a concrete example. Nothing about the parameter is left ambiguous.

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: refreshing the local cache of Zurich legal data. A sibling like zhlaw_search_laws or zhlaw_get_law is clearly a read-of-laws tool, whereas this one is explicitly a cache-maintenance operation, so the agent can distinguish it without opening schemas.

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 <use_case> block gives explicit when-to-use guidance ('nur aufrufen wenn der Cache explizit neu geladen werden soll') plus a when-not ('manual update is rarely needed; cache is auto-filled at start and valid 24h'). This is exactly the routing information an agent needs.

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