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

With no annotations, the description carries the full burden, and it does disclose the headless mode, that answers are returned, that a session_id comes back, and that edits only occur under an explicit flag. It omits permissions/auth requirements, what a profile implies, and any side-effect or concurrency caveats for a tool that can modify files.

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, front-loaded with the core action, followed by the two pieces of routing/behavioral guidance that matter most. No filler.

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?

No output schema and no annotations, so the description must stand alone; it covers the return value and the handoff flow but leaves the profile parameter and its interaction with list_profiles undefined. Adequate for a 3-parameter tool but with a visible 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?

Schema description coverage is 0%, so the description must compensate. It explains allow_edits well but leaves profile ('in a profile') and prompt unexplained, and the relationship to the list_profiles sibling is not clarified.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Run a prompt through Claude Code headlessly') and the headless qualifier implicitly separates it from the screen-oriented sibling open_in_claude_code. An agent can identify the operation without opening 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?

Gives a clear conditional rule for allow_edits ('only when the user has asked for files to be changed') and explains the handoff path via session_id. It does not, however, state when to prefer this headless tool over open_in_claude_code or how profile selection relates to list_profiles.

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 behavioral burden. It usefully discloses that the full session history is preserved, but omits what happens to the headless session (terminated or still live?), whether the terminal must be specified, and any permission or side-effect implications of a state transition.

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

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

Two short sentences, front-loaded with the action and followed by the payoff. Little waste, though the second sentence is more justification than instruction.

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 3-parameter state-transition tool with no annotations, no output schema, and zero parameter documentation, the description should explain the handoff mechanics and the meaning of profile/terminal. It covers purpose and history continuity but leaves the agent guessing about everything else.

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% for all three parameters (session_id, profile, terminal), and the description adds no semantics for any of them. profile and terminal are entirely unexplained in both places, so the description fails to compensate for the coverage 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?

Specific verb and resource: 'Reopen a headless session ... in a real terminal window,' and it ties the operation to the sibling tool ask_claude_code so the agent can place it in the workflow. It does not, however, distinguish itself from open_in_claude_code, which on name alone sounds like an overlapping handoff action.

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 phrase 'picks up exactly where the headless run left off' implies the trigger case (continuing an ask_claude_code session) but never states an explicit when-to-use rule or why an agent would choose this over open_in_claude_code. Usage is inferable rather than instructed.

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. It discloses that each returned entry is a filesystem directory containing a CLAUDE.md, which tells the agent something about what gets returned, but says nothing about ordering, whether the list can be empty, permissions, or any side effects.

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

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

Two short sentences, zero filler, with the core action front-loaded and the explanatory gloss following it.

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 no-argument, read-only listing tool with no output schema, the description is nearly sufficient: it identifies the resource and gives a concrete sense of what each result entry is. Only minor detail about the return shape is absent, which is acceptable at this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate beyond the resource itself.

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 (List) and resource (profiles) and adds a clarifying gloss: profiles are routing targets, each a directory with its own CLAUDE.md. It does not name or contrast with any of the sibling tools (ask_claude_code, handoff_to_terminal, open_in_claude_code), but the operation itself 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?

Usage is only implicitly conveyed via the phrase 'profiles work can be routed to', which hints this is a discovery step before routing/handoff work. There is no explicit when-to-use statement, no prerequisites, and no mention of the related sibling 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?

With no annotations, the description carries the full burden and does well: it discloses the verbatim write, that the brief never goes through a shell, and the no-second-window behavior plus the new_window override. It stops short of saying what the call returns or what happens on success/failure.

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?

Front-loaded with the action, then the selection rationale, then the mechanism and the session-collision rule. Every sentence carries distinct information and nothing is padded.

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?

No output schema exists, so the description could say more about the return value, and the terminal parameter is left unexplained despite 0% schema coverage. Otherwise it covers the action, safety behavior, and side-effect rules thoroughly.

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% for 4 parameters. The description clarifies brief (written verbatim, not shell-interpreted) and new_window (forces a second window), and implies profile via the path template, but terminal is undocumented in both schema and description.

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 concrete verb and resources: writes a brief to <profile>/.claude/HANDOFF.md and opens Claude Code there. Very clear what happens, but it never names or contrasts the siblings (ask_claude_code, handoff_to_terminal), so an agent must infer the boundary from the one usage hint.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

"Use for work the user should drive themselves" gives a clear selection criterion and implicitly separates it from an agent-driven sibling, and the existing-session paragraph tells the user what to do next. No explicit when-not or named alternative, so it stops short of 5.

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