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

No annotations are provided, so the description carries the disclosure burden. It does reveal two non-obvious behaviors: the operation is gated on `confirmed=true`, and results go into a new correction folder. It does not cover error behavior, permissions, idempotency, or what happens when `confirmed` is false.

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 German sentence contains the action, condition, object, and destination with no filler. The key condition is front-loaded before the purpose.

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 two-parameter command with no annotations and no output schema, the description covers the action, condition, object, and destination of the operation. It omits failure/response details, but the low complexity makes that acceptable.

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 coverage, the description has to add meaning, and it does: `confirmed=true` is the required condition and `proposal_id` is tied to the previously displayed suggestion. That goes beyond raw string/boolean type declarations, though it doesn't detail failure or validation behavior.

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 ('Wendet ... an'), names the object ('vorher angezeigten Vorschlag'), and adds the conditional ('nur bei confirmed=true') and destination ('neuen Korrekturordner'). This makes it clearly a follow-up apply operation and differentiates it from the sibling `propose_corrections`.

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 states a precise applicability condition: only when the proposal was previously shown and `confirmed` is true. It doesn't explicitly name alternatives or exclusion cases, but the workflow context (apply vs. propose) 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?

With no annotations, the description carries the behavioral burden; it discloses two key traits: the operation is read-only and errors/warnings are not hidden ('Fehler/Warnungen werden nicht verschwiegen'). However, it does not describe what the diagnosis covers, what the output contains, or any other side effects, so transparency is partial rather than complete.

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 sentence that front-loads the primary operation ('read-only Diagnose') and then adds the error/warning transparency guarantee. No word is wasted.

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, read-only diagnostic tool, the description covers the core operation and error-reporting behavior sufficiently for invocation. However, with no output schema, it stops short of describing the result format, and it gives no selection guidance relative to bridge_health.

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 has zero properties needing explanation, so the baseline of 4 applies. The description adds no input-parameter detail, but none 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?

States a clear action: 'Führt eine read-only Diagnose aus' (performs a read-only diagnosis), which identifies the tool as a non-mutating diagnostic operation. It is specific enough to distinguish from modification siblings like apply_corrections, but it does not differentiate from the closely named sibling bridge_health or specify what exactly is being diagnosed.

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?

No explicit when/when-not guidance or alternative routing is provided. The 'read-only' qualifier hints at safe diagnostic use, but there is no statement about when to choose bridge_doctor over bridge_health or other 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?

With no annotations, the description carries the full disclosure burden. The explicit 'read-only' qualifier is genuinely valuable and prevents the agent from assuming side effects from a tool named 'health'. However, it does not disclose what the check actually probes (reachability, versions, model availability), failure behavior, or whether an unreachable provider could make the call hang.

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 verb front-loaded and the safety qualifier included - no filler, appropriately sized for a zero-parameter tool. The non-English wording is a minor structural concern for reliable parsing.

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?

Adequate for a 0-parameter, no-output-schema health probe: it states the scope (Bridge, Ollama, optional providers) and the call contract (read-only). Remaining gaps - the bridge_doctor distinction and the returned status format - are minor 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?

Zero parameters means the baseline is 4 and the description owes nothing per-parameter. The phrase 'optionale Provider' adds useful semantic context that the check scope auto-extends to optional providers, going beyond the empty schema.

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 ('Prüft' = checks) with clear resources (Bridge, Ollama, optional providers) and the 'read-only' qualifier, so the health-checking purpose is unambiguous. It does not differentiate itself from the overlapping sibling bridge_doctor, and the German wording may parse less reliably for an English-configured agent.

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?

No guidance on when to use this tool vs alternatives. Given that bridge_doctor is a sibling with clearly related semantics, an agent has no criteria for choosing between a health probe and a deeper diagnostic, and no exclusions or recommendations are provided.

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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It states the tool lists models and selects a recommendation, but it does not disclose whether this operation is read-only, whether it accesses the local filesystem, or what 'safe' means in terms of behavioral constraints. It also doesn't explain any potential side effects or prerequisites, such as Ollama being installed.

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 the main purpose (listing models) and then adds the secondary purpose (selection). There is no redundancy or filler; every word serves a purpose. It is appropriately sized for a tool with no parameters and clear functionality.

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 zero parameters and no output schema, the description is fairly complete for a listing tool. However, it lacks details on the output format (e.g., how models are presented, whether the recommendation is a separate field) and any assumptions about the environment (e.g., Ollama must be installed). These are minor gaps but could affect correct interpretation.

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 has no parameters, so the schema requires no description. The description avoids adding unnecessary parameter details, which is appropriate. Since there are no parameters, the baseline is 4, and the description meets that baseline by not introducing confusion.

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 verb 'Listet' (lists) and the resource 'installierte Ollama-Modelle', and includes an additional purpose of selecting a safe recommendation ('wählt eine sichere Empfehlung'). This distinguishes it from sibling tools like bridge_health or run_shared_file, which have unrelated purposes. The purpose is specific, though it could be clearer on what 'sichere Empfehlung' means.

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 a use case for discovering installed models and getting a safe recommendation, but provides no explicit guidance on when to use this tool versus alternatives. There is no mention of when not to use it, nor any reference to sibling tools. The usage context is only implied, not clearly defined.

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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It explicitly states that no files are changed, which is a critical non-destructive trait. This is a strong and relevant disclosure for a proposal tool, though it does not cover other potential behaviors like idempotency or error handling. The key behavior is clearly communicated.

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 sentences long, concise, and front-loads the most important information: the tool generates a proposal and does not modify files. Every word earns its place, and there is no redundancy. The structure is efficient and easy to parse.

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 tool with two parameters and no output schema, the description is thin. It does not explain the parameters, the expected input format, or what a 'correction proposal' entails (e.g., its structure or how it is returned). The only contextual hint is 'nach einer Analyse', but this is vague. Given the low schema coverage and lack of annotations, the description is incomplete for correct invocation.

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 has two parameters with no descriptions, and the tool description provides no explanation of what run_id or program_name mean. With 0% schema coverage, the description should compensate, but it does not mention the parameters at all. This leaves the agent without any guidance on how to fill the parameters correctly, making this dimension a significant gap.

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's function: after an analysis, it creates one correction proposal, and explicitly notes that no files are changed. This distinguishes it from the sibling tool apply_corrections, which presumably applies changes, though the alternative is not named. The verb 'erzeugt' (creates) and the resource 'Korrekturvorschlag' (correction proposal) make the purpose clear.

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 a contextual condition ('nach einer Analyse' – after an analysis), which suggests when to use the tool. However, it does not explicitly state when not to use it, nor does it mention the sibling tool apply_corrections as the alternative for applying the proposal. The usage guidance is implied but not 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?

With no annotations, the description carries the full burden of behavioral disclosure. It mentions external providers and recursive/ZIP processing, but does not disclose whether data is sent to external services, whether the operation is read-only, or what the return behavior is.

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 short and front-loaded with the core operation and input mode, with no filler words. However, it is arguably too terse for a five-parameter tool with no schema-level explanations.

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 and no annotations, so the description must explain enough to invoke the tool reliably. It does not define the semantics of 'task', explain why 'filename' is required, describe return values, or clarify how 'content', 'path', and 'filename' interact.

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 compensate. It clarifies that path or UTF-8 text can be supplied and names providers, but leaves 'task' and 'filename' unexplained, and slightly conflicts with the schema by emphasizing path while 'filename' is required.

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 identifies a concrete operation ('Prüft') on files, ZIPs, or recursive directories involving Ollama and optionally OpenClaw/Anthropic. It gives enough resource and provider context to distinguish it from sibling health/model/correction tools, though it does not explicitly name alternatives.

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 no when-to-use, when-not-to-use, or alternative routing guidance. It states what the tool does and how to provide input, but an agent cannot determine under which conditions to prefer this over sibling tools.

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