mutify - Trau dich raus

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 bar is lower. The description still adds real operational context the annotations lack: a hard cap of 50 results, sort order by start time, that entries are pre-verified, and that each item should surface a mutify_url or ticket_url.

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?

One dense sentence plus a return-shape clause, front-loaded with the core promise (what's on today in Berlin) before the constraints and the portal link. There is little waste, though the parenthetical portal inventory (Karte, Wetter, Klima, Bezirke) is arguably padding.

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 usefully covers the return shape (max 50, sorted, per-item urls, portal link). But it leaves 'kategorie' completely unspecified and offers no guidance on sibling tools, which is a meaningful gap for a filter-bearing discovery tool.

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?

Only two parameters and schema coverage is 50%. The description merely restates that 'datum' can substitute for today, which the schema already documents, and 'kategorie' — an undocumented free-form string with no enum — gets no explanation of accepted values at all.

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 concrete verb+resource in German: it returns 'gepruefte Veranstaltungen in Berlin' for today or a given date, capped at 50 and sorted by start time. That is specific enough to distinguish it from the sibling list-oriented tools, though it never names those siblings 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?

It gives a clear trigger ('Was ist heute (oder an datum)') but no exclusions or alternatives — nothing says when to use termine_suchen or staedte instead of this Berlin-only shortcut, leaving the routing 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 readOnly, idempotent, non-destructive and closed-world, so safety needs no restating. The description adds genuinely new behavioral context: each result carries coordinate, Bezirk, source, source link and license (Wikidata, CC0), plus an attribution obligation ("Bitte mutify.de/berlin als Quelle nennen") that the agent must honor when relaying 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?

Front-loaded with the search purpose, followed by result-field disclosure and the attribution note; no filler sentences. It is dense and somewhat run-on with the parenthetical category list, but every sentence carries 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 no output schema, the description usefully pre-describes the return fields and the derived mutify_termine value, which is exactly the missing piece. The remaining gap is invocation detail: the max cap and its default, sort order, and whether bezirk must be an exact name.

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 must carry the load. It explains suchtext, kategorie and bezirk thematically, but adds no matching semantics, no example Bezirk values, and never mentions the max result-limit parameter (1-50, no documented default), leaving one of four parameters unexplained.

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 (Orte in Berlin) and the three filter dimensions (Text, Kategorie, Bezirk), then enumerates the covered place types (Museen, Buehnen, Clubs, Maerkte ...). This makes the scope unmistakable and clearly separable from the event-oriented siblings like termine_suchen.

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 only implied: an agent can infer that this is the lookup for venues/places, while the note that mutify_termine counts upcoming events hints that events themselves come from elsewhere. There is no explicit when-to-use/when-not statement and no named alternative such as termine_suchen or berlin_heute.

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. The description adds genuinely new behavioral context: only cities with *currently published* events are returned, and each entry carries a hit count. It stops short of describing ordering, scope of the counts, or the response shape, which matters somewhat since there is 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?

A single short sentence with the filter condition and the returned payload front-loaded; no filler or redundancy.

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 zero-parameter read-only lookup with no output schema, the description conveys enough to call it correctly: what is listed, under what freshness condition, and that counts are included. Only minor gaps remain (ordering of results, exact shape of the count field).

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 tool takes zero parameters and the schema is an empty object, so there is no parameter meaning for the description to add. The baseline for a parameterless tool 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?

"Liefert die Staedte mit aktuell veroeffentlichten Terminen und Trefferzahl" names a specific verb (deliver) and a specific resource (cities), plus the filter criterion (currently published events) and an output field (hit count). It does not explicitly distinguish itself from siblings like orte_suchen or termine_suchen, 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?

The description gives no when-to-use or when-not-to-use guidance and never names an alternative such as termine_suchen or orte_suchen. An agent must infer that this is a discovery/overview call from the purpose statement alone.

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 fully covered by structured data. The description adds one genuinely new behavioral fact: a not-found case returns the literal 'nicht verfuegbar' rather than erroring, which is useful for the calling agent, but nothing else is disclosed.

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?

A single front-loaded sentence with the operation, its parameter, and the fallback value, with no filler. Every clause carries 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 lookup with rich annotations and no output schema, the definition is close to sufficient, but the quoted 'nicht verfuegbar' return is unexplained (empty result vs. sentinel value) and there is no hint on sourcing the termin_id. These are modest gaps for a tool this simple.

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 schema description coverage at 0% for the single parameter, the description does clarify that termin_id is the identifier of a single event, adding some meaning beyond the bare integer type in the schema. It does not specify the identifier format, origin, or validity constraints, so the compensation for the coverage gap is only partial.

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 ('Liefert einen einzelnen Termin') and the lookup key ('nach termin_id'), which distinguishes it from the plural search sibling termine_suchen. It stops short of naming the sibling explicitly, so the differentiation is inferred from singular vs. plural rather than stated.

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?

Using termin_id implies the tool is for fetching one already-known event, which implicitly contrasts with termine_suchen, but no when-to-use or when-not-to-use guidance is given. There is no statement about where an agent should obtain a termin_id before calling.

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 past the annotations (readOnly, idempotent, non-destructive) by disclosing the 50-result cap, the date-then-distance sort order, the affiliate nature of ticket_url and that results without a ticket link are equally valid, the meaning of status 'abgesagt' and datenstand_warnung=true, and an explicit prompt-injection warning about 'beschreibung' being data. It also explains how entfernung_km behaves when umkreis_km is omitted.

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 purpose, result cap and sort order, then grouped into short value-bearing notes about links, status, data freshness and distance. The final sentence is long and carries two separate ideas about entfernung_km, 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?

There is no output schema, so the description correctly carries the burden of naming return fields (mutify_url, ticket_url, status, datenstand_warnung, entfernung_km, umkreis_km) and their interpretation. Only the unexplained 'kategorie' parameter and default date-range behavior keep it from being fully complete for a 6-parameter search tool.

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 only 50%, but the description compensates for the most consequential gaps: it explains that omitting umkreis_km widens the search to the surrounding area and that umkreis_km appears in the response, and it ties nur_mit_ticketlink to the ticket_affiliate concept. 'kategorie' remains entirely undocumented in both schema and description, and no guidance is given on the von/bis window beyond the schema's format.

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 ("Sucht Termine bei mutify") and immediately adds the result cap and sort order, so the agent knows this is a search/listing tool. It never names the sibling 'termin' or 'orte_suchen', so the boundary between event search and place search must be inferred from the names alone.

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: the agent can infer this is the tool for finding events, and the description does prescribe presenting mutify_url/ticket_url per result. There is no explicit 'use this when X, use termin/orte_suchen when Y', and no prerequisites or exclusions are given.

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 readOnly, idempotent, non-destructive and closed-world behavior, so the description's added value is the freshness contract: hourly updates, per-report quelle/quelle_url/lizenz, and the meaning of datenstand_warnung=true (data older than 3 hours). That is genuine behavioral context an agent cannot get from the annotations or 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?

A single dense paragraph, front-loaded with scope, followed by filters, then return fields and the freshness flag. Every clause carries information; there is 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 read-only, no-output-schema query tool, this covers scope, sources, filter vocabulary and result-shape hints (source, URL, license, staleness flag). The remaining gaps are the undocumented max cap and the lack of expected format for bezirk and suchtext.

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 0%, so the description must carry the parameter burden. It explains art values (oepnv, aufzug, strasse — omitting 'alle' from the enum) and gives concrete linie examples (U8, S41, M10), but bezirk and suchtext get only a name, and the max parameter is not mentioned at all.

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 concrete resource (current Berlin traffic reports, updated hourly) and enumerates the covered modes and sources: S-Bahn, U-Bahn, Tram, Bus, Regionalverkehr (VBB), elevators out of service, and road construction/closures (VIZ Berlin). This is far more specific than the siblings (berlin_heute, termine_suchen, orte_suchen), so an agent can tell immediately what domain this serves.

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 described content and by the filter list (art, linie, bezirk, suchtext), so an agent knows how to narrow results. However, there is no explicit statement of when to prefer this over siblings like berlin_heute, nor any exclusion or prerequisite guidance.

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