Klar Daheim

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the parenthetical 'schreibt nie' largely restates structured data. It does add one genuinely new fact — that only the text of an approved ('freigegebenen') file is returned, implying a visibility restriction — but nothing about missing-file behavior or return shape.

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, front-loaded with the action and resolution method. The read-only parenthetical partly duplicates the annotations, which is slight waste but keeps the safety framing visible.

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 annotation coverage and no output schema, the definition covers what the tool does, how the target is identified, and that text is returned from approved files only. Missing only edge-case behavior for unknown names.

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 single 'name' parameter already documents alias examples, so the description's own example list ('kosten', 'faq', 'zuschuss.md') is redundant. Baseline 3 applies since the schema carries the parameter burden.

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 ('Liest eine Datei des Hubs') plus the resolution mechanism ('per Name oder Alias') with concrete alias examples. It does not name or rule out the sibling tools list_content/search_content, so differentiation is left implicit.

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 lookup-by-name/alias framing implies the use case (fetch one known file), but there is no explicit guidance on when to prefer this over search_content or list_content, nor any stated prerequisite such as the file having to be approved.

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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the parenthetical '(Read-only: liest eine einzelne Datei, keine Änderungen.)' largely restates structured data. The one genuinely new behavioral fact is 'falls vorhanden' – the target file may not exist – but the description does not say what is returned in that case (empty result, error, or null).

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 the resource and the filename front-loaded. The parenthetical slightly duplicates the readOnlyHint annotation, but it is brief enough that the redundancy costs little.

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, no-output-schema tool the description covers what the tool reads, but with no output schema it should state the return shape (raw markdown text, parsed content, or nothing when absent). As written, an agent knows what file is targeted but not what a successful or failing call yields.

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, so there is no parameter semantics to explain and the schema cannot be a source of ambiguity. Baseline 4 applies; nothing in the description misleads about inputs.

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 specific verb and resource: it returns the SEO-/GEO keyword map, and it even identifies the concrete artifact (seo-keyword-map.md). That is far more precise than the sibling names get_content or get_status, though it never explicitly contrasts itself with those siblings, which could also plausibly return file content.

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 when-to-use or when-not-to-use guidance and no alternative is named. The only hint is the conditional 'falls vorhanden', which tells the agent the file may be absent, but nothing tells it whether get_content is the fallback or when this tool should be preferred over the generic content readers.

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, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The parenthetical '(Read-only: liest nur das Dateiverzeichnis, keine Änderungen.)' largely restates that, adding only the detail that it reads a file directory. The useful extra is the enumeration of returned fields, not the behavior disclosure.

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, front-loaded with what is returned. The trailing parenthetical is partly redundant with the annotations, which is the only wasted space.

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 tool with no output schema, the description is adequately complete: it lists the returned information (version, file count, guidelines) so the agent knows what to expect from the call. Only the exact shape of the response and the guidelines' content remain unspecified.

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, so the baseline is 4. The description correctly adds nothing about inputs, and there is nothing about inputs left ambiguous.

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 the public status of the Klar-Daheim MCP, naming concrete contents (version, number of Ratgeber files) plus the content guidelines. That is clearly distinct from the sibling tools (get_content, list_content, search_content), though it never names them 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 only implied: an agent can infer this is the informational/metadata endpoint rather than a content-retrieval one. There is no explicit statement of when to call it, when not to, or which sibling to prefer for actual content lookups.

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, and the parenthetical largely restates that, so the safety profile adds little. What does add value beyond structured fields is the disclosed return content (title and path per file) and the scope limitation to the hub's own directory with no external systems, which is useful given 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?

Two sentences: purpose and return values first, behavioral caveat second, so it is front-loaded and short. The parenthetical repeats annotation-covered facts (read-only, no changes) and could be trimmed to just the directory/external-systems point.

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 parameterless, non-destructive listing tool with no output schema, the description supplies everything needed: what is listed, what is returned, and that it touches only the hub directory. Minor omissions such as ordering or behavior on an empty hub are acceptable at this complexity.

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 no parameters, so the schema cannot be enriched and the baseline of 4 applies. The description correctly does not invent filtering options, which keeps the no-argument contract unambiguous.

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 specific verb and resource ('Listet alle öffentlichen Markdown-Dateien des Klar-Daheim-Inhaltshubs') and even states the returned fields (Titel und Pfad). The scope word 'alle' implicitly contrasts with the single-item sibling get_content and with search_content, but no sibling is named explicitly, so differentiation is left partly 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?

Use is implied (enumeration of everything published) rather than stated; there is no explicit 'use this when…, use search_content instead when…' guidance and no mention of prerequisites or limits. For a zero-parameter listing tool the implied usage is fairly unambiguous, but the description never routes the agent between siblings.

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, yet the description still adds real behavioral context: matching is case-insensitive, the corpus is limited to local shared Markdown files, and results are snippets rather than full documents. The parenthetical read-only remark partly restates the annotations, which keeps it from a 5.

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 with the search semantics front-loaded and the read-only note trailing. The parenthetical slightly duplicates the annotation information, which is the only wasted space.

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 read tool with full annotation coverage, the description covers purpose, scope, matching behavior and the shape of returned results, so no output schema is needed. It stops short of describing result ordering or what happens when nothing matches.

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%, so both query and max_results (default 20, max 50) are already documented in the schema. The description adds no further parameter meaning, such as the minimum query length of 2 or how snippets are chosen — baseline 3 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?

States a specific verb and scope: case-insensitive full-text search across all public hub files, returning filenames and text snippets. This clearly separates it from list_content/get_content, 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?

Usage is only implied — search when you need to locate files containing a term. There is no explicit when-to-use/when-not guidance pointing to list_content for browsing or get_content for retrieving a full file.

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