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

Annotations only provide destructiveHint=false, leaving the behavioral burden mostly on the description. The description usefully conveys that the tool supports API and CLI modes and that CLI mode uses an existing subscription instead of API credits. However, it doesn't disclose side effects like whether the provider is persisted, whether it overrides existing providers, or what happens on invalid configurations.

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 exactly two sentences and immediately states the purpose and the two supported modes. There is no redundancy, and the most valuable scope 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?

Given the high complexity (10 params, no output schema), the description provides a helpful high-level framing that complements the fully self-describing schema. The only clear gap is that the description doesn't cover return values or post-add confirmation behavior, but the schema details all parameters well.

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. The description doesn't add significant value beyond the schema; it merely echoes the CLI/API distinction already present in field descriptions. It does not clarify conditional requirements or the relationship between adapter, backend, and command beyond what the schema contains.

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 (Add) and explicit resource (new AI provider for brainstorming), and distinguishes this from siblings like list_providers and brainstorm tools. It clearly identifies both supported modes: OpenAI-compatible APIs and local CLI providers.

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 to use the tool: adding a provider for brainstorming, with either API or CLI. It doesn't explicitly say when not to use it or name alternatives like list_providers, but the context is specific enough for an agent to select it over purely brainstorming or listing 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?

The description discloses detailed side effects beyond annotations: API mode calls external APIs with billing implications, hosted mode spawns sub-agents with environment models, and participation behavior via brainstorm_respond when participate=true. It also notes that if mode is omitted, the tool returns options. This is far richer than the readOnlyHint alone.

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 long but well-structured with clear sections, bolding, and lists. Every sentence conveys required operational details—nothing is redundant. While it could arguably be trimmed, the complexity of the tool's dual modes justifies the length. It is not flabby; it is dense and purposeful.

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 9 parameters, no output schema, and complex branching (API vs hosted), the description covers prerequisites, alternatives, and step-by-step invocation guidance. It explains the full flow including how to use sibling tools (list_providers, brainstorm_respond, brainstorm_collect) and the host's role. It does not describe return values, but that is acceptable since no output schema is provided and the focus is on executing the tool properly.

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% coverage for all parameters, so the baseline is 3. The description adds extra meaning by explaining how mode interacts with user choice, prompts the use of list_providers, and clarifies the participate flag's role (via brainstorm_respond in API mode). It also clarifies the models format ('provider:model') implicitly through examples in the schema description. This elevates it above the baseline.

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 runs a multi-round brainstorming debate between multiple AI models. It specifies the verb (run), the resource (debate), and distinguishes itself from sibling tools like brainstorm_quick (presented as a quick version) and brainstorm_respond/collect (which are sub-components).

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 explicitly instructs the agent to ask the user to choose a mode before calling, explains both modes with one-liners, and directs the agent to use list_providers for available providers. It also tells what to do in hosted mode (ask which models to use, spawn sub-agents) and clarifies when to set mode='api' vs 'hosted'. Clear guidance on when to use and how to proceed.

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 include readOnlyHint: true, which already signals a non-destructive operation. The description adds transparency by explaining the three return outcomes (next prompt, synthesis prompt, final result) and the nested structure of responses required, without conflicting with the annotation. It could mention whether the session state is updated, but the return-value description suffices.

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 verbose but appropriately detailed for a multi-step workflow. It avoids redundancy and clearly structures the steps and return types. Some minor redundancy exists (e.g., repeating 'brainstorm' mode), but it remains readable and direct.

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 readOnlyHint already provided, the description covers the tool's purpose, usage sequence, return types, and parameter details. It lacks mention of error conditions or session expiration, but for the tool's complexity, this is sufficient. Overall, it gives the agent enough context to use the tool 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?

All two required parameters (session_id and responses) are fully described in the schema with clear semantics. The description further clarifies the 'model' parameter by giving examples ('sonnet' or 'haiku') and emphasizes the requirement to collect responses for each model, enhancing the schema's clarity. Coverage is 100%.

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: 'Submit collected model responses for a hosted brainstorm session.' It specifies the exact action (submit responses) and the resource (brainstorm session), and distinguishes it from siblings by referencing the workflow of the `brainstorm` tool.

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 explicit when-to-use guidance: after receiving prompts from `brainstorm` (mode='hosted') or a previous `brainstorm_collect` call. It also explains the required workflow (execute each prompt per model using the model parameter) and lists the three possible return types, giving clear context for invocation.

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?

Annotation `readOnlyHint: true` tells the agent this is a read operation. The description adds useful behavioral context: parallel model firing, compact comparison output, no debate rounds, no synthesis delay, and the under-10-second expectation. It does not mention potential rate limiting or model failure behavior, but this is beyond the essential disclosure for this 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, front-loaded with the core behavior, and each sentence earns its place: what it does, the key guarantees, and when to use it vs. the alternative.

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 4-parameter schema, readOnlyHint annotation, and no output schema, this description is sufficiently complete. It covers the tool's behavior, timing, return format (compact comparison), and the sibling-tool boundary. No critical context for selection or invocation is missing.

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 four parameters are already well-documented. The description adds little parameter-level meaning beyond what the schema states, though it indirectly emphasizes the default behavior of firing all models in parallel.

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: getting instant multi-model perspectives via parallel calls. It explicitly distinguishes this from the `brainstorm` sibling tool by contrasting quick versus deep analysis with rounds and synthesis.

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?

Provides explicit usage guidance: use for quick second opinions, snap decisions, or diverse perspectives fast. It also names the alternative `brainstorm` for deeper analysis, making the decision between siblings clear.

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 description says 'Submit' and 'call' implying a write operation, but the annotation readOnlyHint: true indicates read-only. This contradiction makes the score 1 per instructions.

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 moderately concise, front-loads the main purpose, but includes instructional details (like 'Read all responses carefully') that could be trimmed without losing clarity.

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 schema descriptions, the description provides sufficient context on when to use the tool and what to do, though it does not address edge cases like multiple calls or error handling.

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 both session_id and response, and the description adds contextual flavor (e.g., 'substantive contribution') but no new semantic information 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?

Clearly states the tool submits Claude's response for the current round, and distinguishes from siblings by referencing the brainstorm tool and the condition after external models return.

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?

Explicitly says to call this tool after the brainstorm tool returns external models' responses, and provides guidance on what to do (read, engage, not summarize) and the automatic next-round behavior.

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

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

Annotations already declare readOnlyHint: true, so the safety profile is clear. The description adds process transparency: multiple models review independently, findings are synthesized and deduplicated, and it states the output verdict types. This enriches understanding beyond the annotation without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise—three sentences with a clear front-loaded purpose. Each sentence adds value: what it does, how it works, and when to use it. No filler or 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?

Without an output schema, the description compensates by outlining the output structure (severity, file/line refs, verdict). It covers the main workflow and use cases, leaving parameter specifics to the schema. Adequate for an agent to invoke correctly, though it could mention how to format the diff or handle errors.

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% with all six parameters explained. The description itself adds minimal parameter detail beyond stating 'Pass a diff' and mentioning the verdict values. Since the schema already covers parameter meaning, the description does not significantly enhance understanding, matching the baseline.

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 'Multi-model code review' and specifies the action: pass a diff and receive structured findings with severity, file/line references, and a verdict. It also lists concrete use cases (PR reviews, code audits, pre-commit checks), distinguishing it from sibling brainstorming 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 explicitly says 'Use this for PR reviews, code audits, or pre-commit checks,' providing clear when-to-use guidance. It does not explicitly mention when not to use it or alternative tools, but the context is specific enough for typical scenarios.

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, so the read-only behavior is covered, leaving the description free to add detail about the inclusion of locally installed CLIs and their subscription-based billing, which is useful. It doesn't describe the response structure or pagination, but the absence of parameters suggests a simple listing, so this is adequate.

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, no fluff. The first clearly states the primary purpose, and the second adds crucial context about the local CLIs and billing model. Every word earns its place, and it's front-loaded with the key action.

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 simple (no params, no output schema), but the description covers the essential details: what is listed, the nuance of local CLIs versus API-based, and the billing context. It could mention that the output is in a structured format, but the lack of output schema and the simplicity of the task don't demand more.

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 zero parameters, the description's job is to clarify what the tool returns, which it does by specifying the content: providers, default models, and the local CLI variants. Since there are no parameters, it maximizes clarity about the output, making this a strong score.

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 lists configured AI providers and their default models, and it explicitly distinguishes its scope by including locally installed agent CLIs. This differentiates it from sibling tools like brainstorm (which likely generates ideas) and add_provider (which modifies providers).

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 implies usage as a discovery tool for available providers, noting that some run on subscriptions rather than metered API credits, which helps in selecting providers for brainstorming. However, it doesn't explicitly state when not to use it or brand it as a read-only complement to add_provider; the context is clear but exclusions are absent.

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