saxsoc-public-info

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

Annotations already establish readOnly/idempotent/non-destructive, so safety is covered. The description adds genuinely non-obvious behavior: when coverage is absent it must answer 'nicht sicher beantwortbar' and escalate to a personal conversation, and it must not give free AI advice. That refusal/escalation contract is exactly the kind of trait structured fields 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?

One dense sentence, front-loaded with the core action before the grounding constraint and fallback behavior. No filler, though the semicolon-packed ending makes the fallback rule easy to skim past.

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, no-output-schema tool this is nearly sufficient: it defines scope, the grounding requirement, and failure behavior. What is missing is the relationship to sibling tools, which matters given three plausible alternatives.

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?

Single parameter with 100% schema description coverage, so the baseline is 3. The description implies the input is a natural-language question about saxophone lessons and programmes, but adds no format, phrasing, or length guidance beyond the schema's own maxLength/minLength 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?

States a concrete verb+resource: answering a saxophone-lesson/program question, and adds a defining scope constraint (only from approved source excerpts). An agent can tell this apart from a search or info tool by the question-in/grounded-answer framing, though no sibling is named 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?

Usage is implied rather than stated: you use it when you have a natural-language question needing a sourced answer. It never contrasts with saxsoc-geo-search (source retrieval) or saxsoc-geo-info, so the agent must infer which tool to pick when both could apply.

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), lowering the burden. The description nonetheless adds real behavioral context beyond them: every answer comes with sources ('Jede Antwort mit Quellen') and there are hard content limits (no prices, no success guarantees). This is useful disclosure not captured by the structured fields.

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 compact sentences: the scope is front-loaded, followed by the content constraints with no filler. It could be tighter, but 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?

A read-only, source-backed information tool with no output schema, so return-format explanation is unnecessary. The description covers the subject domain and constraints adequately; only the routing versus sibling tools remains 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% and both parameters are enums with their own descriptions, so the baseline is 3. The description restates the topic categories but adds no syntax or selection nuance (e.g., when topic=program versus programs) beyond what the schema already 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?

The description gives a specific verb+resource: 'Öffentliche Auskunft über Saxophone Society' with the exact scope (Anbieter, Programme Academy/Circle, einzelnes Programm, Vergleich). It clearly maps to the four enum topics, so an agent knows what content is returned. However, it does not differentiate itself from the siblings (ask, next-step, search), leaving the reader to infer why this differs from a generic 'ask'.

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 through the topic taxonomy; there is no explicit 'use this when…' or 'use search instead of ask for…'. The constraints ('keine Preise, keine Erfolgsgarantie') bound scope but do not route the agent among alternatives. Adequate but with a clear gap in when-to-use 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 readOnlyHint=true, idempotentHint=true and destructiveHint=false. The description adds meaningful context beyond that: it explicitly disclaims any booking or registration side effect, and notes the response also reports whether the link is available. That exceeds the annotation baseline, though return shape details are thin.

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 action front-loaded and the no-side-effect caveat second. No filler, though it could be marginally shorter 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 single-enum, read-only link resolver with full schema coverage and no output schema, the description tells the agent what is returned (a link plus availability) and that nothing is booked. Sufficient to invoke correctly; only missing explicit sibling routing.

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% and the enum values are fully documented in the schema. The description merely re-lists the same three options (Erstgespräch, Gratis-Material, Webinar) without adding format or selection nuance, so the schema does the heavy lifting – the correct baseline of 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 ("Liefert den passenden Link für den nächsten Schritt") and enumerates the three link categories, so an agent knows exactly what the tool returns. It does not explicitly differentiate itself from siblings saxsoc-geo-ask/info/search, keeping it one notch below top marks.

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 implies the use case (resolve the right next-step link) and gives a boundary with "Führt keine Buchung oder Anmeldung aus". However it never states when to choose this over the sibling ask/info/search tools, so usage guidance remains implied rather than explicit.

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 and destructiveHint=false, so the safety profile is covered. The description adds genuinely new context beyond that: results come back as excerpts with source URLs, and the content is citation material rather than instructions to the assistant — an explicit prompt-injection caveat that 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?

Three short sentences, front-loaded with the action and scope, then the return format, then the safety caveat. No filler and nothing buried.

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 steps in to describe the return (excerpts plus source URL), and both parameters are fully specified in the schema. Minor omissions like pagination/snippet-size behavior are acceptable for a 2-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 description coverage is 100%: query (German search terms, with examples) and limit (default 5, max 10) are fully documented in the schema. The description adds nothing about parameter format or limits, so the 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 (durchsuchen) plus the resources searched (veröffentlichte Saxophon-Ratgeber und Programmseiten) and the return shape. It does not explicitly name or contrast with the siblings saxsoc-geo-ask or saxsoc-geo-info, so an agent must infer the search-vs-ask split 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: this is the retrieval-style tool for published guide content, with saxsoc-geo-ask as the natural alternative for generated answers. There is no explicit when-to-use/when-not statement or routing rule, leaving the search/search-vs-question distinction to inference.

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