mcp-server

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

With no annotations, the description carries the full behavioral burden and does a solid job: it reveals that the tool combines two different search sources, and it explicitly discloses that every hit contains a canonicalUrl field along with the instruction to display that link proactively. It does not discuss read-only guarantees, rate limits, or permissions, but the described behavior is sufficiently transparent for a lookup-style tool.

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 three sentences with no filler: the first sentence states the core purpose and source logic, the second adds strategic priority, and the third gives a concrete, actionable output instruction. Every sentence earns its place and the most important information is front-loaded.

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 two-parameter tool with no output schema, this description is largely complete: it names the query semantics, the combined search sources, and the critical output field plus display behavior. The only notable gap is that it does not describe the broader result shape or clarify how results from the two source strategies are merged, but the essential calling context is present.

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 already describes both parameters with 100% coverage, so the baseline is 3. The description adds no additional parameter-level detail beyond restating that query can be a title, composer, or instrument, which the schema already states. Limit behavior is documented only in the schema, not enhanced by the description.

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 ('Prüft') and resource ('ob es eine B-Ware-, reduzierte oder gebrauchte Alternative gibt') and clearly frames the query scope as title, composer, or instrument. It also distinguishes itself from general searches by explicitly mentioning the combined Noten-B-Ware-Flag and Katalog-29-Suche logic, which separates it from siblings like search_bargain_stock or search_sheet_music.

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 clear context for when the tool should be used: whenever a user asks whether a B-ware, reduced, or used alternative exists for a title, composer, or instrument. It also labels it as a 'Zentraler USP-Case,' signaling priority. However, it does not explicitly state when not to use it or how it compares to the sibling search_bargain_stock tool.

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?

With no annotations, the description carries behavioral disclosure and does add value: it states B-Ware status is included and every result has a canonicalUrl field. It does not cover error/not-found behavior, but the read-only nature is evident from 'Liefert'.

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 with no filler, front-loaded with the core function and followed by a key routing rule and an output-field instruction. Every sentence earns its place.

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 2-parameter detail lookup with no output schema or annotations, the description covers purpose, scope, result contents, and a required link-handling behavior. It is slightly light on failure/error behavior and the full response shape, but adequate for selection and execution.

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 50%; productId is well explained in the schema, and the enum values for catalog are self-explanatory. The description adds only implicit parameter meaning via 'Noten oder Instrument' and does not explain when or whether catalog is needed.

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 ('Liefert Detailinformationen') and a precise resource ('einzelnen Artikel ... per Artikelnummer'), and explicitly states it is not a substitute for catalog enumeration. This clearly distinguishes it from the sibling search 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?

It gives a clear usage context: use when you have an article number and need details for a single item. The 'Kein Ersatz für eine Katalog-Enumeration' sentence is an effective exclusion, though it does not name sibling tools explicitly.

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?

With no annotations provided, the description carries the burden of behavioral disclosure. It adds concrete behavioral details: returns a limited result list (max 20) and each hit contains a canonicalUrl field that should be displayed with specific product mentions. It does not mention sorting, pagination, or error cases, but for a simple search tool this is meaningful coverage.

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 compact: two sentences, with the search scope front-loaded, followed by the result cap and the canonicalUrl display instruction. Every sentence adds useful operational information 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 search tool with two well-documented parameters and no output schema, the description adequately covers the key context: what is searched, the result cap, and the expected URL field. It could be more complete by describing additional result fields or typical search behavior, but it is sufficient for a basic 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%: both query and limit are already described in the input schema. The description does not add much parameter-level meaning beyond noting the 20-item cap, which matches the schema. Baseline 3 applies because the schema already handles parameter documentation.

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 a specific verb ('Sucht') and resource ('Bestand an B-Ware, Vorführ- und gebrauchten Instrumenten (Katalog 29) von musikalienhandel.de'). It distinguishes this tool from siblings like search_instruments and search_sheet_music by emphasizing the discount/used-instrument catalog scope.

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 a clear context: this is for searching B-ware, demo, and used instruments from catalog 29, calling it a 'central USP'. However, it does not explicitly state when to prefer this tool over alternatives such as search_instruments, nor does it name exclusions. Usage is implied rather than explicitly guided.

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?

With no annotations provided, the description carries the full behavioral disclosure burden. It adds important behavior beyond the schema: results are limited to 20, the tool is not meant for exhaustive enumeration, each hit includes canonicalUrl, and the agent must proactively show that link when naming products. This is substantial and useful behavioral 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 two focused sentences with no filler. It front-loads the core purpose, then immediately adds the key behavioral constraints and output-handling instruction. Every sentence earns its place.

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 two-parameter search tool with no output schema or annotations, the description covers purpose, limitations, and result presentation sufficiently. It lacks only minor context such as explicit ordering or empty-result behavior, and it does not mention sibling alternatives, but the core information an agent needs to invoke and use the tool correctly is present.

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 schema describes both parameters fully (query as free text, limit with default and max), so schema description coverage is 100%. The description mentions the max of 20 results, which aligns with the schema but adds no new parameter-level semantics beyond what the schema already states.

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 action ('Sucht'), a specific resource ('GEWA-Instrumenten- und Zubehörsortiment von musikalienhandel.de'), and distinguishes it from related catalog tools by noting it is not a full catalog enumeration. This makes the tool's role clear relative to siblings such as search_sheet_music and search_bargain_stock.

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 when to use the tool: whenever searching the GEWA instrument/accessory assortment. It also gives a limitation ('keine vollständige Katalog-Enumeration'), which acts as a when-not signal, but it does not explicitly name alternatives or state conditions for choosing search_bargain_stock, search_sheet_music, or get_product.

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?

With no annotations provided, the description carries the full disclosure burden. It usefully discloses that the result list is capped at 20, includes a B-Ware hint, excludes full-text descriptions, does not enumerate the whole catalog, and that each hit has a canonicalUrl that must be shown. This is strong behavioral transparency for a search tool.

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 compact and well structured: the first sentence states the purpose, the second covers limitations and the required canonical link behavior. Every sentence adds necessary information, and there is no waste or repetition of the schema.

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 that there is no output schema and no annotations, the description covers the important operational details: search scope, result limit, exclusions, and how to handle canonicalUrl in responses. It does not mention empty-result behavior or authentication, but it provides enough for an agent to invoke the tool and use its results correctly.

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 already documents all five parameters with 100% coverage, so the baseline is 3. The description adds only marginal parameter-level meaning, such as indicating that publisher/Verlag is a valid search criterion even though there is no dedicated publisher parameter.

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 action (searching the sheet music catalog of musikalienhandel.de) and the main search criteria (title, composer, instrumentation, publisher). It also sets clear expectations about results (max 20 hits, no full-text descriptions, no full catalog enumeration), which helps distinguish it from sibling search 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?

The description implies when to use the tool: whenever an agent needs to find sheet music in the catalog. However, it does not explicitly name sibling tools or provide when-not-to-use conditions such as 'for product details use get_product instead', so 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.