1820.ch – Telefonbuch Schweiz

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

Annotations already declare readOnlyHint and idempotentHint, so the safety profile is covered. The description still adds useful context by specifying that results are public directory entries and that narrowing is optional rather than required. It does not discuss pagination or result ordering, but with annotations and a 1-20 limit in the schema the remaining gap is small.

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, zero filler, and the core behavior plus scope constraint is front-loaded before the sibling routing advice. Every clause carries information an agent needs.

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 full schema coverage, annotations, and an output schema present, the description need not explain return values or formats. It covers purpose, scoping, and the alternative route, leaving only minor edge cases (e.g., invalid slug handling) unaddressed.

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 the baseline is 3; the schema already documents category slugs, lang, limit, and location formats. The description adds only a light reinforcement of the optional location narrowing, so it does not meaningfully exceed what the schema provides.

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

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

States a specific verb and resource ('Lists public directory entries in one business category') plus the precise scope narrowing (locality/postcode/canton). It also explicitly names the sibling it is not, so an agent can distinguish it from search_swiss_directory without reading 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 description gives an explicit routing rule: use this tool for category browsing and 'use search_swiss_directory instead for a free-text query.' That is a clear when-to-use-this vs. when-to-use-the-alternative statement, with the selecting condition 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 readOnlyHint and idempotentHint, so the safe-read profile is covered by structured data. The description adds one useful behavioral detail ('when the entry has them', i.e. optional fields may be absent) and implies the detail is public, but discloses nothing about error behavior for a bad entry_id or rate limits.

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 the core fetch behavior and its distinguishing payload front-loaded before the routing sentence. No filler or repetition.

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 annotations covering safety, the description needs only purpose and routing, both of which it supplies. It stops short of covering failure modes (invalid/expired entry_id) or pagination, which is a minor gap given the otherwise complete structured metadata.

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 (entry_id provenance, lang enum plus default) are already fully documented in the schema. The description's restatement of entry_id/public_id adds no syntax or format detail beyond it, 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 (fetches) and resource (full public detail for one directory entry) and names the identifier used (entry_id/public_id). It also enumerates the payload (phone numbers, opening hours, links), so the agent knows exactly what this returns versus the sibling search/browse 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 routes usage: 'Use get_directory_entry for phone numbers and opening hours; use search_swiss_directory or browse_business_category to find an entry_id first.' This tells the agent both the selecting condition and the required prerequisite step, with the alternatives 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 cover readOnlyHint and idempotentHint, so safety is off the table. The description adds genuine behavioral value by disclosing the empty-result-list outcome when no public listing exists — an edge case not derivable from annotations and only implied 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?

Two tightly written sentences, no filler, with the core operation and accepted formats front-loaded before the edge-case note.

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 annotations covering the safety profile, a full-coverage input schema, and an output schema, the description only needed to add the non-obvious empty-result behavior — which it does. Nothing an agent needs to invoke 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 description coverage is 100%, so both parameters are already documented in the schema. The description restates the accepted phone notations (duplicating the phone_number description) and adds nothing about the lang enum. Baseline 3 applies when the schema does the heavy lifting.

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 (looks up) and resource (public directory entry) scoped to Swiss phone numbers, with the accepted input notations named. An agent can distinguish this from get_directory_entry or search_swiss_directory without opening the 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?

Usage is implied by the name and by the 'reverse lookup' framing, but the description never states when to prefer this over search_swiss_directory or get_directory_entry, nor any prerequisites. Adequate but no 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 (readOnlyHint=true, idempotentHint=true), so the description correctly focuses on behavior beyond that: the AND-matching semantics of 'matches ALL words' is a genuinely useful disclosure that explains why short keywords succeed. It stops short of describing result ordering or what a truncated/no-match response looks like, which keeps it from 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 sentences, each load-bearing: purpose/scope first, then query-matching behavior and the query/location split, then alternatives and the deeper-lookup sibling. No restatement of the title and 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?

An output schema exists, so return values need no explanation. With 100% parameter coverage, annotations carrying the safety profile, and the description covering scope, matching semantics, and sibling routing, nothing an agent needs to call this 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 is 3, but the description adds a cross-parameter constraint the schema cannot express: place names belong in location and never in query, plus the AND-matching rule that constrains query construction. That is real added meaning over per-field descriptions.

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 ('Full-text search over the Swiss public phone/business directory (1820.ch)') and immediately distinguishes itself from siblings by naming both browse_business_category and get_directory_entry with their respective roles. 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?

Gives explicit when-to-use guidance ('short keyword works best'), a placement rule ('put any place name in location, not query'), and a named alternative with the condition that selects it ('For "business type X in place Y", browse_business_category with a category slug is an alternative'). This is the full when/when-not/alternative triad.

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