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

With no annotations provided, the description carries the full behavioral burden. It does disclose the key mutation trait — that discovered engines are 'automatically sync[ed] into your Antigravity vault' — and the network-probing behavior. However, it does not disclose side effects like whether existing vault entries are overwritten, whether probing can be disruptive, or any failure behavior when no servers respond. Adequate but not rich.

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 dense sentence is front-loaded with the verb and target ('Auto-scan local network ports for running AI servers'), and the port enumeration is genuinely useful operational detail rather than padding. It is slightly dense — seven server/port mappings plus a three-part outcome clause — but nothing 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 zero-required-parameter detection tool, the description covers the core behavior well: what is scanned, what is discovered, and what happens to the vault. Since there is no output schema, the description could more explicitly specify the return shape (though 'lists their active models' hints at it). Minor gaps — no mention of the no-results case or how vault conflicts are resolved — keep it just short of 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 100% — all three optional parameters (auto_sync with its default and effect, timeout_ms with its default, custom_ports with an inline example) already carry full semantics in the schema. The description adds no parameter-level detail beyond the schema, so the baseline of 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?

The description names a specific action ('Auto-scan local network ports' / 'Detects online engines') with a concrete resource ('running AI servers', 'Antigravity vault') and enumerates the exact servers and ports probed (Ollama, LM Studio, vLLM, etc.). This clearly distinguishes it from siblings like llm_test_connection, llm_list_models, and llm_manage_providers — an agent can tell this is the discovery/sync tool without opening a schema.

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 but never stated explicitly. The description conveys this is for detecting and syncing local AI servers, but it does not name alternatives (e.g., llm_test_connection for testing a single known endpoint, llm_manage_providers for manual vault edits) nor provide when-not-to-use guidance. The sibling names hint at the boundaries, but the description itself leaves the routing to inference.

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 full responsibility for disclosing behavioral traits. It mentions the actions, but does not warn that 'clear' empties the entire cache (a destructive, irreversible operation) or that 'prune' only removes expired entries. While the enum descriptions in the schema clarify the actions, the tool description itself omits risk-related context, which is a notable gap for a mutating 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 a tight two-sentence summary that front-loads the core purpose ('Manage the Dynamic Response Cache') and then lists the four actions in a single sentence. There is no redundancy or fluff; every word contributes to understanding the tool.

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?

The tool has only two parameters (one enum) and no output schema. The description covers the actions and their effects reasonably well, but it omits any caution about the destructive nature of 'clear' and does not hint at what return values to expect (e.g., stats output). Given the mutating capability, the description should at least flag irreversibility. 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 100%: both 'action' and 'limit' are described in the schema with clear meanings. The tool description does not add new parameter-level information beyond what the schema provides—it only repeats the action names. Since the schema already does the heavy lifting, the description meets the baseline for this dimension.

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 purpose: 'Manage the Dynamic Response Cache for external LLMs' and enumerates the specific actions (inspect hit rates, view savings, prune, clear). It is distinct from all sibling tools, which focus on generation, compression, or model management, so there is no ambiguity about its 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 implies when to use the tool—whenever cache management is needed—and lists the four concrete actions. It does not explicitly name alternatives or exclusions, but given that no sibling tool overlaps with cache operations, the context is clear enough for an agent to select it appropriately.

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 burden. It discloses parallel execution and the use of an identical prompt, but omits other behavioral aspects such as required credentials, potential for network calls, error handling, or return format. This is minimal transparency for a tool that makes external calls.

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, focused sentence that front-loads the core action and provides concrete examples. 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?

The tool is moderately complex with nested candidate objects, but the description does not describe the output format, error behavior, or how to interpret results. With no output schema, this is a significant 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?

The schema already provides descriptions for all three parameters, and the description adds no additional parameter-level information. Since schema coverage is 100%, the baseline score of 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?

The description states a specific verb ('benchmark and compare') with a clear resource ('responses to the exact same prompt') and scope ('across multiple models or providers in parallel'). It also names example providers, making the purpose unmistakable and distinguishing it from potential siblings like llm_council.

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 when comparing models but does not explicitly state when to use it vs alternatives. It does not mention any sibling tools or exclusions, leaving the decision to the agent's inference.

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 burden and mostly fulfills it: it discloses the exact transformations (strip redundant whitespace, duplicate lines, deep library frames), the semantic preservation guarantee, and that token savings metrics are returned. The precise return payload — whether the compressed text accompanies the metrics — is left implicit, a moderate gap 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 with zero filler: the purpose and transformation details are front-loaded, and the return-value hint earns its place as a deliberate second sentence. Technical specificity ('deep library frames', 'token savings metrics') is included without bloat.

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, pure-transformation tool with no output schema and no annotations, the description covers what it processes, how it transforms the input, and what it returns. The only notable gap is the unspecified return format, which is mitigated by the tool's simplicity.

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 the baseline is 3, but the description adds meaning beyond the schema: it specifies acceptable input forms (prompts, code, logs, stack traces) and the compression strategy, which the schema's bare 'The text or code to compress' does not convey.

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 ('Compress any prompt, code block, log output, or stack trace') and names the mechanism (RTK Smart Compression). None of the 12 sibling tools (llm_generate_image, llm_query, llm_cache, etc.) perform compression, so an agent can immediately distinguish it.

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 enumerates the applicable input types (prompt, code block, log output, stack trace), providing clear context for when to invoke it. It does not name an alternative or state when-not-to-use conditions, but no sibling tool competes for this task, so the context is sufficient.

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?

It accurately discloses the core orchestration behavior: parallel broadcast to multiple members, automatic judge critique/cross-examination, and delivery of a single consensus solution. However, with no annotations at all, the description leaves important operational traits unstated, such as external API/cost implications, credential requirements, and behavior if a member fails.

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 with no filler. The core mechanism is front-loaded, and the examples ('Dahl, DeepSeek, Groq, Ollama') add useful specificity without bloating the text.

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 complex 6-parameter nested tool with no annotations and no output schema, the description gives a solid conceptual frame and tells the agent what kind of result to expect ('single optimal consensus solution'). It does not cover return shape, failure behavior, or operational caveats, so it is only minimally complete for safe and 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 already provides 100% parameter description coverage, including defaults for judge and members. The description reuses the same conceptual labels like 'Chief Justice' and 'council members' without adding parameter-specific syntax, constraints, or relationships beyond the 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?

The description opens with 'Multi-Model Consensus & Council Deliberation' and clearly states it broadcasts problems in parallel to multiple LLM members and synthesizes via a Chief Justice. This gives a specific verb, resource, and workflow that conceptually separates it from single-query siblings like llm_query. It does not explicitly contrast sibling tools, so it just misses the top score.

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 names concrete use cases — 'complex problem, code architecture, or security audit' — giving an agent clear when-to-use context. It does not name alternatives or state when not to use the council, so it provides clear context without explicit exclusions.

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 does disclose two important behaviors: the image is saved locally and the tool returns an embeddable file path. It does not mention authentication requirements, what happens when no provider is specified, rate limits, or failure behavior.

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 compact sentences. The main action is front-loaded in the first sentence, the provider examples are parenthetical and useful, and the second sentence conveys the output expectation without waste.

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?

The description covers the core contract: generate, save locally, return an embeddable path. However, with six parameters, no output schema, and no annotations, it omits operational details such as how the provider is resolved when only prompt is given, whether endpoint_url is required, and the concrete format of the returned file path.

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 the baseline of 3 applies. The tool description adds no parameter-level detail beyond what the schema already provides; for example, endpoint_url is already documented in the schema as an 'Ad-hoc /v1 base URL supporting /v1/images/generations.'

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 a specific action and resource: 'Generate an image' via 'ANY external /v1 endpoint', then lists concrete examples such as SiliconFlow, Together AI, and DALL-E. It also states the outcome ('saves the generated image locally and returns an embeddable file path'), which clearly differentiates it from siblings like llm_generate_video.

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 you need to generate an image through a supported external /v1 endpoint. However, it does not explicitly state when not to use it, nor does it point at alternatives such as llm_generate_video for video generation or other non-generation tools.

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 mentions 'external /v1 endpoint' but does not disclose authentication requirements (api_key), potential costs, output format, or whether the operation is synchronous. The description implies a write operation but lacks details on side effects or response handling.

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 sentence that front-loads the core action. The list of provider examples adds some value but is somewhat verbose. Overall, it is concise and to the 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?

With 6 parameters and no output schema, the description is insufficient. It does not explain the expected return value, error handling, or prerequisites like providing an API key. The agent would need to infer usage from parameter names and external knowledge, which is not ideal for a complex 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?

The schema description coverage is 100%, so the baseline is 3. The description adds context about provider examples (SiliconFlow, Together, MiniMax) but does not clarify parameter relationships or usage beyond what the schema provides. It does not compensate for any missing semantic details, but the schema is adequate.

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 action ('Generate a video') and the resource ('video'), and mentions the external /v1 endpoint, which distinguishes it from sibling tools like llm_generate_image. However, it does not explicitly contrast it with alternatives, so differentiation is somewhat implied rather than stated.

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 guidance on when to use this tool versus other generation tools like llm_generate_image or llm_query. The description does not mention specific scenarios, prerequisites, or exclusions, leaving the agent to infer usage from the tool name and context.

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 mentions the 'reset' action but does not warn about the destructive nature of clearing the ledger, potential data loss, or any side effects. It also does not describe the return format or whether the operation is read-only by default. The description is vague about the consequences of the 'clear' action, which is a significant gap for a tool that can mutate state.

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 with no filler. The primary purpose (retrieve analytics) is front-loaded, and the reset capability is mentioned in the second sentence. Every phrase contributes value, and the structure is clear and efficient.

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?

The tool has 4 optional parameters, no required ones, no output schema, and no annotations. The description explains the high-level return (analytics) but does not specify the exact output structure, the effect of 'clear' beyond resetting, or any limitations like pagination. Given the moderate complexity and missing output schema, the description should provide more detail about the response format and side effects. It is adequate but leaves gaps.

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 each parameter (limit, model, action, provider) already has a clear description. The tool description adds context about what analytics are retrieved (cost, tokens, latency) and mentions provider names, but it does not add meaning beyond what the schema already provides. The baseline of 3 applies because the schema 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 the tool retrieves cost, token usage, and latency analytics from a specific ledger, and can reset statistics. It names the resource and specific breakdowns, distinguishing it from sibling tools like llm_query or llm_generate_image which are about querying or generation. The verb 'Retrieve' and 'reset' are explicit and the scope is unambiguous.

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 makes it clear this is the analytics tool, and the action parameter (get/clear) implies when to use each. However, it does not explicitly state when to use this vs alternatives or mention any exclusions. Given siblings are clearly different in function, the context is sufficient, but there is no explicit guidance like 'use this when you need ledger statistics' or 'not for generation'.

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 are absent, so the description carries the full burden. It discloses the HTTP method (GET) but does not explicitly state this is a read-only operation with no side effects, nor does it explain authentication requirements, rate limits, or error behavior.

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 sentence with zero filler and front-loads the core purpose. It is appropriately sized for the tool's simplicity, though it omits usage details.

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 should at least hint at the return format (e.g., list of model IDs) or parameter selection rules. It provides neither, leaving the agent without enough information to call the tool correctly in all cases.

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 the schema already documents all three parameters. The description adds no additional meaning about how parameters interact (e.g., whether endpoint_url overrides provider) or when each should be supplied.

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 action ('List available models') and the specific resource ('OpenAI-compatible /v1 endpoint'), and it names the exact HTTP call (GET /v1/models). This distinguishes it from generation, query, and connection-testing siblings.

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 versus alternatives like llm_test_connection, nor how to choose among the three optional parameters (provider, endpoint_url, api_key). The agent is left to infer usage.

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 present, so the description carries the full burden. It mentions list/add/set/update but does not disclose that remove and set_fallback_cascade are destructive or config-mutating, whether changes persist immediately, or how API keys are stored. This leaves behavioral risk under-specified for a management 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?

A single front-loaded sentence with no filler and clear verb phrases. It is concise and easy to scan, though the compactness sacrifices completeness of action enumeration.

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 an 8-parameter tool with a 7-value action enum and no annotations or output schema, the description is too thin. It ignores remove, get_active, and set_fallback_cascade actions, and gives no usage context for the active default flow. An agent would need to inspect the schema to discover half the tool's behavior.

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 all eight parameters are already documented structurally. The description adds light context that base_url corresponds to endpoints and api_key to key updates, but it does not explain provider_key, default_model, or fallback_cascade beyond what the schema states. A baseline 3 is appropriate given the schema coverage.

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 resource ('configured LLM providers in your Antigravity vault') and enumerates several distinct actions (list, add endpoint, set active, update API keys). This clearly differentiates it from sibling inference/query tools such as llm_query and llm_list_models. Though it omits some schema actions, the core purpose is unambiguous.

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 is provided on when to use this tool versus alternatives; it does not name sibling tools or state conditions for choosing it. An agent must infer from the name that this is for provider configuration rather than model interaction. With siblings like llm_list_models and llm_test_connection, explicit routing would be valuable.

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 full responsibility for disclosing side effects. It mentions saving to a vault, but it does not disclose that the tool can also update or delete presets, nor does it explain persistence, permissions, or other mutation consequences. This is a significant gap for a CRUD-like 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 short and front-loaded with concrete examplescase. The first sentence could be slightly tighter since 'Manage and inspect' overlaps with the second sentence's action list, but overall it remains concise and scannable.

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?

The description covers the core list/view/save functionality but omits mention of update and delete actions that the schema supports, and it does not describe return values in the absence of an output schema. The examples compensate somewhat, but for a 7-parameter CRUD tool with no annotations, the description is 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 100%, so the schema already documents all seven parameters in detail. The description adds useful example values for the `name` parameter but does not add meaning beyond the schema, 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?

The description clearly identifies the resource ('expert System Personas and Prompt Presets') and gives concrete example names. It names the primary actions ('list', 'view', 'save'), which distinguishes it from the sibling generation and query tools without needing to open the schema.

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: when the agent needs to list, inspect, or save presets. However, it does not explicitly state when not to use it or mention any alternatives, so the usage guidance is 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?

No annotations are present, so the description carries the disclosure burden. It discloses ad-hoc endpoint overrides, reasoning extraction, and custom system prompts, but it does not mention that the tool makes external network calls, may incur token costs, reads/writes a local cache, or enables automatic fallback on provider errors. These are meaningful behaviors for an agent, though the description is not misleading and does not contradict any 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?

Two compact sentences with no filler. The core action and resource are front-loaded, followed by a short feature list that adds value without restating parameter names or repeating schema content.

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 15-parameter tool with no annotations and no output schema, the description is not fully complete: it omits streaming, caching, fallback cascade, token compression, and cost/network implications. The rich 100%-coverage input schema compensates for parameter-level detail, making the description minimally viable but not comprehensive.

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?

All 15 parameters have schema descriptions (100% coverage), so the schema already carries the per-parameter semantics. The description adds only high-level grouping such as 'custom system prompts' and 'ad-hoc endpoint overrides' rather than detailed parameter meaning, which keeps it at the baseline for high schema coverage.

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 the specific verb 'Query' plus a clear resource ('external LLM via OpenAI-compatible /v1 endpoint'), lists concrete provider examples, and names distinct capabilities like reasoning extraction and endpoint overrides. This clearly differentiates it from the sibling generation and management tools, even without naming them.

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 tool is for general text queries to any external LLM and highlights useful capabilities, but it does not explicitly state when to use this tool versus siblings like llm_compare, llm_autodetect, or llm_generate_image. No exclusions or alternative routing guidance is provided, leaving the choice to inference.

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 present, so the description carries the full behavioral burden. It discloses that the tool checks connectivity, latency, and credentials, which adds useful context, but it does not state whether any state is modified, what request is sent, or whether the tool is safe to run repeatedly. The description is not contradictory, but it leaves side-effect ambiguity.

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 front-loaded sentence with no filler. It conveys the tool's purpose, scope, and key checks (connectivity, latency, credentials) without redundant wording.

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 three optional parameters and no output schema, the description provides a reasonable overview but omits practical details like what happens when neither provider nor endpoint_url is supplied, and what form the test results take. An agent could invoke it, but might not know how to interpret the response or choose between the two target parameters.

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 schema already explains each parameter. The description adds context that provider and endpoint_url are alternative targets and that api_key relates to credentials, but it does not go beyond the schema in explaining parameter interactions or optionality.

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 action ('Test connectivity, latency, and credentials') and a clear resource scope ('any LLM endpoint or configured provider'). This distinguishes it from sibling generation/query tools like llm_query and llm_generate_image, which serve different purposes.

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 tool is for verifying connectivity or credentials before use, but it does not explicitly state when to prefer it over alternatives or provide exclusions. An agent has to infer usage from the phrase 'test connectivity, latency, and credentials' rather than being told.

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