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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world behavior, so the safety profile is covered. The description adds genuinely useful context beyond that: it reports on the *local* CLI specifically and reveals it delegates to `claude auth status`, clarifying scope and failure surface.

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 zero filler. The core action and target are stated first, with the implementation detail appended compactly.

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?

An output schema exists so return values need no explanation, annotations cover safety, and there are no parameters to document. For a simple read-only status probe, nothing further is required 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 tool takes zero parameters, so the baseline is 4. The description correctly implies no inputs are needed, and there are no parameter semantics to misrepresent.

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 (report) and resource (local Claude Code CLI sign-in state), and names the underlying command. It is clearly distinguishable from the sibling tools, which handle cloud sessions and follow-ups rather than local auth.

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 by the name and by 'whether the local CLI is signed in' — an agent can infer this is a precondition check. However, there is no explicit statement of when to call it (e.g., before other Claude Code operations) and no mention of alternatives or 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?

Despite annotations already declaring readOnlyHint=false/openWorldHint=true/idempotentHint=false, the description adds substantial non-obvious behavior: the pseudo-terminal requirement (CLI rejects piped stdout), the parsed vs. `cli` fallback output shape, the CWD resolution rule, and the WORKSPACE_NOT_TRUSTED failure with the CLAUDE_MCP_TRUST_CWD=1 escape hatch. These are exactly the environment-specific behaviors an agent cannot get from the schema or 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?

Four sentences, front-loaded with the action, then output contract, then environment/failure behavior. Each sentence carries operational weight, though the parsing-failure sentence is somewhat dense and could be tightened without losing meaning.

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 creation tool with an output schema, the description covers the action, the return contract, the runtime environment, and the one failure mode that blocks success. An agent has everything needed to invoke it correctly and to interpret a failed call.

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 explains both parameters including the CLAUDE_CLOUD_ENVIRONMENT_ID override, which the description does not restate or extend. Baseline 3 is appropriate since the description adds no format, constraint, or default detail beyond the structured fields.

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 verb and resource ('Create a new Claude Code cloud session') and even names the underlying mechanism ('claude --cloud'). It is unambiguous, though it never explicitly contrasts itself with the sibling tools claude_send_followup or claude_auth_status, so it stops short of a 5.

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 rather than stated: an agent can infer this is the entry point that precedes claude_send_followup, but there is no explicit when-to-use/when-not-to-use guidance or alternative routing. The operational preconditions it does give (PTY requirement, trust requirement) are about mechanics, not tool selection.

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 the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=true), so the bar is lower. The description adds that the message is 'queued' (asynchronous delivery), which is useful behavior beyond the annotations, but says nothing about auth requirements, delivery guarantees, or whether an in-flight turn blocks the queue.

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 zero filler; the scope ('existing') and mechanism are packed in 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?

An output schema exists, so return values need no explanation, and the tool only has two well-documented params. The description is nearly sufficient, missing only prerequisites for obtaining a valid session and the async implications of queuing.

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 coverage is 100%: both params are fully documented with patterns and length bounds. The CLI form `claude --cloud <session> -p <message>` maps role to argument, adding marginal clarity, but duplicates what the schema already conveys. Baseline 3 is correct.

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 (queue a follow-up message) and resource (an existing Claude Code cloud session). The word 'existing' implicitly distinguishes it from claude_create_cloud_session, but no sibling is named 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?

The word 'existing' implies a session must already be present, giving implied usage context. However, it never states when to prefer this over creating a session or how to obtain a session id, so guidance is only implied.

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