Job Clerk

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds genuinely new context beyond the annotations: it returns full public employer text plus a canonical citation URL, and it discloses that unavailable adverts return errors rather than empty results — a meaningful failure-mode hint.

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 short sentences with no wasted words, and the core operation plus return payload are front-loaded before the edge-case note about unavailable adverts.

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 detailed, and the description nonetheless notes employer text and citation URL alongside error behavior for missing adverts. For a one-parameter read tool this is nearly complete; only the relationship to the lese_stellenanzeige sibling is left 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 0% and the single property is just typed 'string' with no documented format. The description compensates by specifying that the id is a search result ID, which tells the agent where the value must come from. It stops short of stating the ID's format or where exactly to find it.

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 ('Fetch a public physician advert') plus the identifier source ('by its search result ID'), which clearly distinguishes it from the search siblings like search or suche_arztstellen. However, it never differentiates itself from lese_stellenanzeige, an apparent near-duplicate read-by-id sibling, leaving the agent to guess which read tool to pick.

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?

'By its search result ID' implies the caller should first obtain an ID from a search tool, which is useful implied sequencing. Beyond that there is no explicit when-to-use, when-not-to-use, or named alternative, so the routing decision against lese_stellenanzeige or search remains unstated.

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, and the description still adds real value: it warns that employer-wide statements are not a commitment for this specific position, which is an interpretation caveat found nowhere in structured data. "Liest nur öffentliche Daten" partly restates readOnly but usefully scopes which data is reachable. Missing: behavior on an unknown or malformed publicId.

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 dense sentences, front-loaded with the verb, the key, and the returned fields, followed by two short caveats. No padding, no repeated title, nothing that could be cut without losing 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?

For a one-parameter read tool with full annotations and no output schema, the description compensates by naming the returned data classes and by flagging the interpretive caveat. What remains uncovered is failure behavior for an invalid publicId and any explicit routing to the batch sibling, which keeps it short of a 5.

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 is a single parameter with 100% schema description coverage, and the schema already explains both the pattern and where to obtain the publicId (search result or the last segment of a canonical URL). The description only restates that the lookup is by publicId, adding no new meaning. 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?

"Liest eine Anzeige anhand ihrer publicId" gives a specific verb plus resource and the identifying key, then enumerates the content returned (Arbeitgebertext, Vergütung, Berufserlaubnis-Belege, Quellen). The singular "eine Anzeige" implicitly separates it from the plural sibling lese_stellenanzeigen, but that sibling is never named, so the differentiation is left to inference.

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 makes clear this is a single-record read, and the closing sentence draws a negative boundary ("führt keine Bewerbung aus"), which tells the agent this is not an action tool. However it never says when to prefer it over lese_stellenanzeigen (batch), fetch, or search, nor does it state prerequisites such as obtaining the publicId first — that hint lives only in the schema.

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 behavior, so the remaining burden is light. The description adds genuinely useful semantics beyond them: the ten-id cap and, importantly, that failures are reported per ad rather than aborting the whole call, which tells the agent to expect partial results.

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 short sentences, zero filler, with the batch limit stated first and the return/error behavior second. Nothing can be removed without losing meaning.

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 single-parameter, read-only tool with no output schema, the description covers scope, the cap, and per-item success/failure reporting, which is most of what an agent needs to call it safely. The only real gap is the origin and format of publicIds.

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 carries the param burden, and it only partially does: it restates the maximum of ten ids but says nothing about where a publicId comes from or its format. The uniqueness and minimum-one constraints live only in the schema, and an agent must open it to learn the id shape.

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 uses a specific verb ("Liest") with a bounded scope ("bis zu zehn ausgewählte publicIds") and states the per-item outcome, so an agent knows this is a batch read of job ads. It does not explicitly name the singular sibling lese_stellenanzeige, so the batch-vs-single distinction must be inferred from the plural and the ten-id limit.

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?

Batch usage is implied by "bis zu zehn ausgewählte publicIds", but the description never says when to prefer this over lese_stellenanzeige for a single ad, nor what to do when more than ten ids are needed. The usage context is present but not stated as a routing rule.

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?

The annotations already establish that this is a safe, read-only, idempotent, non-destructive operation in a closed world. The description adds useful behavior by stating that it returns filter codes and hit counts and accepts the same filters as the search without page and sort, but it does not explain the return shape, whether counts are exact or approximate, or any 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?

The description is two compact sentences with no filler, and the core purpose is front-loaded. The second sentence efficiently clarifies parameter compatibility and exclusions.

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 17-parameter, read-only facet tool with no output schema, the definition covers the main purpose and parameter relationship to search. It still leaves gaps around how the filter codes and hit counts are returned, what 'aktuelle Suche' means in practice, and when the tool should be preferred over inspecting search results directly.

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 description adds meaningful semantics by saying the tool accepts the same filters as the search, minus page and sort, which helps an agent understand the 17-parameter set as a compatible subset rather than an unrelated schema. Individual parameter meanings are largely left to the schema, whose description coverage is moderate at 65%.

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: it returns available filter codes and hit counts for the current search. It also clarifies that it takes the same filters as the search but without page and sort, which distinguishes it from actually running a search, though it does not explicitly name the sibling search tool.

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 phrase 'zur aktuellen Suche' and 'Nimmt dieselben Filter wie die Suche' imply this should be used alongside a search to inspect filters and counts. However, it does not explicitly say when to call this tool instead of the search tool or whether it should be called before or after a search.

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 without the description. The description adds the useful behavioral note that results are IDs plus canonical citation URLs, which steers the agent to fetch, but says nothing about matching behavior (title vs. full text), result caps, or ranking.

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 short sentences, no padding, with the core purpose front-loaded and the disambiguation and return-shape notes following in priority order. Every sentence changes how an agent would call the tool.

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?

A one-parameter read-only tool with an output schema and rich annotations needs little more than this, and the description covers purpose, the query semantics trap, sibling routing, and the return shape. It falls short of 5 only because it omits how keyword matching works and what happens with multi-word queries.

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 burden and does so meaningfully: it defines query as keyword text rather than a natural-language filter expression, which is exactly the misunderstanding that would cause a bad call. It does not mention the 1–300 character constraint or how multiple keywords combine, leaving a small gap.

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 ('Search German physician job adverts by keywords') and immediately bounds the scope of the tool versus the sibling that handles filters. The agent can distinguish this from suche_arztstellen and from the lese_* 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 narrows usage by warning that 'query is keyword text, not a natural-language filter parser' and routes location/role/exclusion/pagination needs to suche_arztstellen. It lacks an explicit positive 'use this when you only have free-text terms' clause and says nothing about the lese_* or fetch siblings' place in the workflow beyond 'Returns IDs for fetch', but the when-not guidance is clear.

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 behavior. Beyond that, the description discloses return characteristics (belegte Angaben, Quellen, nextPage) and a checking limitation, which is genuinely additive for a tool with no 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?

Four dense sentences, front-loaded with the core action, then filter inventory, then the q rule, then return values and limitations. Every sentence carries information and none restate the title verbatim.

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 19-parameter search tool with no output schema, the description covers what is returned (sources, nextPage) and what is not checked. The gaps are minor — page/sort handling and the ort_id plus umkreis dependency are only in the schema, not the description.

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 63%, so much of the semantics already comes from the schema. The description enumerates the filter families (Ort, Fach, Karrierestufe, Arbeitgeber, Einrichtung, Berufserlaubnis, Ausschlüsse) and clarifies that q is residual, but does not explain land, page, sort, or the ort_id/umkreis pairing constraints.

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?

Uses a specific verb and resource ('Sucht öffentliche Arztstellen in Deutschland') and clearly bounds scope to public job listings. It does not explicitly differentiate itself from siblings like lese_stellenanzeigen or suche_orte, though the schema's reference to suche_orte for ort_id gives implicit context.

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?

Provides a useful usage rule ('q enthält nur verbleibende Suchwörter') and a negative scoping statement ('Andere Bedingungen prüft die Suche nicht'). However, it never states explicitly when to pick this tool over lese_stellenanzeigen or search, leaving the agent to infer the 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 declare readOnlyHint, idempotentHint, non-destructive and closed-world, so safety is covered structurally. The description usefully adds that one input name can yield multiple places, which the agent cannot infer from annotations. It says nothing about no-match behavior, matching fuzziness, or result ordering, so the addition is real but modest.

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 short sentences, front-loaded with the resolution behavior and the cardinality caveat directly after. Nothing is padded, but the final sentence is unclear and does not earn its place as written.

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 one-parameter, read-only, non-destructive tool with full schema coverage and an existing output schema absence that is unproblematic for a simple resolver, the description covers the essentials including the one-to-many result risk. Missing are failure behavior and what the returned 'stabile Kennungen' are used for downstream.

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?

With 100% schema description coverage, the single 'suche' parameter is already fully documented as a place name or postal code, so the baseline is 3. The description restates both accepted input types but adds no format or matching detail, and the sentence about 'Kennung und Ortstext zusammen' is ambiguous enough that it could mislead an agent into thinking an identifier may be passed.

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 uses a specific verb ('Löst ... auf' / resolves) on a specific resource (Ortsnamen oder Postleitzahlen) and states the outcome (verfügbare Orte und stabile Kennungen), so an agent knows this is a name/postal-code resolution tool rather than a general lookup. It does not explicitly contrast itself with the generic 'search' or 'suche_arztstellen' siblings, which keeps it below 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?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling is named as an alternative. The closing sentence 'Die Suche nimmt Kennung und Ortstext zusammen' further muddies rather than clarifies when the tool applies, since the schema accepts a single text string.

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