ecoExperten Energieausweis

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds meaningful behavioral context: it requires a matching email, only outputs status on match, and explicitly excludes personal or building data from the response. This goes beyond the annotations.

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 concise: three sentences, each with a clear purpose. The first states what it does, the second gives prerequisites and verification behavior, the third specifies response content. No wasted words.

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 (two params, no nested objects, output schema exists), the description is nearly complete. It covers purpose, prerequisites, verification, and response scope. It is slightly vague about error behavior when credentials don't match, but that's a minor gap.

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 carries the full burden. It explains both parameters: bestellnummer has a specific format (EA-XXXXXXXX) and email is the one associated with the order. This adds valuable meaning beyond the schema's bare names.

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 clearly states that the tool returns the processing status of an order placed via this assistant. It specifies the resource (order) and the action (query status), and distinguishes from siblings like bestellung_aufgeben (create) and energieausweis_info via the 'über diesen Assistenten aufgegebenen' qualifier.

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 clearly states when to use the tool: when you have the order number and email address of an order placed through this assistant. It also specifies the matching requirement. However, it does not explicitly name alternatives or exclusions, so it stops short of a 5.

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?

Beyond annotations like readOnlyHint=false, the description discloses substantial behavioral traits: the order is initially pending, a confirmation link is sent, it becomes binding only after recipient confirmation, unconfirmed orders expire after 48 hours at no cost, and both agb_akzeptiert and zahlungspflichtig_bestaetigt must be true. It also explains test_modus simulation and server-side GEG validation. No annotations are contradicted.

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 appropriately sized for a 37-parameter order tool. It is front-loaded with the headline summary, then uses short paragraphs for flow, consent, validation, and test mode. Every sentence adds value, with no redundancy or 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?

Given the tool's complexity (37 params, 22 required) and the existing output schema, the description covers the essential operational context: price, payment method, pending/binding states, email confirmation, expiry, consent requirements, GEG validation, and test mode. This is sufficient for an agent to understand the tool's full lifecycle and invoke it responsibly.

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 0% schema description coverage, the description compensates for the most semantically critical parameters: it explains that agb_akzeptiert and zahlungspflichtig_bestaetigt are required consents, without which the server rejects the order, and that test_modus=true simulates without side effects. However, it does not cover the many building/consumption parameters (e.g., energy_source, has_vacancy, consumption_1), leaving them to rely on their field names alone.

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 opens with 'Verbrauchsausweis bestellen (59,00 EUR, Kauf auf Rechnung) — mit E-Mail-Bestätigung', a clear verb+resource with price and payment method. The rest of the description details the order flow, making it unmistakable that this tool creates a pending order, distinct from siblings like bestell_status and bestellung_pruefen.

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 provides clear context for when to use it: to place a binding order after consent, with test-mode simulation available. It does not explicitly contrast with sibling tools or state 'don't use for status checks', but the context strongly implies this is the action tool for creating a new order.

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, so the agent knows it's read-only. The description adds that it's a pre-check (Vorprüfung) and is kostenlos (free). No contradiction. It could mention validation results behavior, but overall it adds meaningful context.

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 one paragraph with bullet-like lists. It is fairly concise but uses some abbreviations and German terms that may make it less clear. Could be more structured and readable.

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 high parameter count (29) and complexity, the description gives a high-level overview but lacks details on validation rules, handling of optional fields, and what the output looks like (though output schema exists). It is adequate but not fully complete.

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 description only explains a subset of parameters (gebaeudetyp, Adresse, etc.). Many parameters like keller, kuehlung, lueftung are not described. The description does not compensate for the lack of schema descriptions on many fields.

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 clearly states 'Verbrauchsausweis-Bestellung vorprüfen' which means pre-check an order for an energy consumption certificate, and emphasizes 'OHNE zu bestellen' (without ordering). It lists key fields, making the purpose very specific. It distinguishes itself from siblings like 'bestellung_aufgeben' (which places the order).

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 says 'Vorprüfung ohne Bestellwirkung', indicating it is a validation step. It implies usage before ordering, but does not explicitly state 'when to use' vs. alternatives like 'bestellung_aufgeben'. Still, the context is clear enough.

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 declare readOnlyHint true and destructiveHint false, which aligns with the description stating it provides product information. The description adds specifics about what information is provided (prices, documents, legal prerequisites), going beyond annotations.

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 a single, concise sentence that is front-loaded with key information. Every word earns its place without 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 simple read-only informational tool with zero parameters and an output schema, the description adequately covers the purpose. It could mention the output format, but the output schema handles that.

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 input schema has zero parameters, so schema coverage is 100%. No parameter details are needed in the description, and the baseline score of 4 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?

The description clearly states the tool provides product information about ordering an energy certificate for residential buildings, including prices, required documents, and legal requirements. It distinguishes itself from sibling tools that handle order management.

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 usage for informational queries about the energy certificate product, but does not explicitly state when to use this tool versus alternatives like bestellung_aufgeben or bestell_status. Usage context is somewhat implied by the sibling names.

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