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

No annotations are provided, so the description carries the full behavioral burden. It does disclose the disconnect side effect, but says nothing about whether the session becomes unrecoverable, what happens to buffered terminal output, or what error results from an invalid/already-closed session_id.

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, covering both the action and its effect. It is arguably too terse given the gaps elsewhere, but nothing in it 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?

An output schema exists so return values need no explanation, but this is a state-changing tool with no annotations, an undocumented required parameter, and no stated prerequisites or failure modes. The description is too thin for an operation that tears down a device connection.

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% and the single parameter has no documented meaning in the schema. The name 'session_id' is fairly self-explanatory, but the description does not say where the id comes from (e.g. open_session) or what format it takes, so it 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?

States a specific verb and resource ('Close a session') plus a concrete side effect ('disconnect from the device'), which clearly contrasts with the sibling open_session. It stops short of explicitly naming the inverse tool, but the pairing is obvious from the sibling list.

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 when-to-use guidance, no prerequisites, and no mention of alternatives such as leaving a session open or checking session_status first. Usage is only implied by the tool name.

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 'every call goes through the client's permission approval gate', which is a non-obvious side effect. However, it is silent on session lifetime/timeouts, resource cleanup, and the need to pair with close_session, leaving meaningful gaps for a long-lived connection 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 opening sentence front-loads the core purpose, and the remaining prose is organized by concern (target description, routing, serial, permission gate). It is dense but for an 11-parameter tool most sentences earn their place; the route/jump-host explanation is the only slightly expansive part.

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 not be explained. Given the tool's complexity (11 params, discriminated route union, credential backends, opt-in flags), the description covers protocols, routing, serial, and the approval gate but omits the remaining safety flags and the session lifecycle. Adequate but noticeably incomplete for a tool this rich.

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?

Top-level schema description coverage is 0%, so the description must compensate and does so for roughly half the parameters: host/port/protocol, credentials-as-references, the single-hop 'socks'/'proxyjump' route, and serial needing an absolute /dev/tty* path plus allow_serial=true. It says nothing about allow_telnet, host_key_policy, allow_plaintext_password, legacy, or the relationship between protocol and the route discriminator.

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 ('Open a raw interactive terminal session and keep it open') and distinguishes itself from siblings by pointing to terminal_write for follow-up hops inside the same session. It is clear what the tool produces, though it never quite names the alternative tools for session reuse or states that the returned handle feeds terminal_read/terminal_write.

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 gives real when-to-use guidance: use 'proxyjump to reach a bastion quickly and run further ssh or telnet hops yourself with terminal_write inside the same session', and use 'protocol="serial" with an absolute /dev/tty* path' for local console cables. It stops short of explicit exclusions (e.g. when to reuse an existing session vs open a new one), but the context provided is above average.

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. 'Bounded slice' hints at pagination, but it does not say whether reads are non-destructive, whether offset is a cursor over accumulated output that persists, whether the call blocks until new output arrives, or how much output a default limit returns.

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 tight sentence with the action and scoping mechanism front-loaded. Nothing is padded, though there is too little content rather than too much.

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 shape need not be described. However, for a paged read tool with zero annotation coverage and three undocumented parameters, the description omits the semantics an agent needs: pagination/cursor behavior, default limit, and offset units.

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 covers offset implicitly and 'bounded' gestures at limit, but session_id — the only required parameter — is never explained, nor are offset units (characters vs bytes vs lines) or the default/absence behavior of limit.

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 (Read) and resource (accumulated session output) with the scoping mechanism (bounded slice by offset). It is clear on its own, but it does not distinguish itself from the sibling terminal_read, which an agent could plausibly confuse with this 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?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as terminal_read or session_status. The agent must infer from the name alone whether this is the right read tool.

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. "Return" implies a read, but it does not state whether the call is safe/idempotent, what happens when the session_id is unknown or expired, whether authentication is needed, or whether the returned state is cached or live.

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, which is appropriate for a one-parameter read tool. It is slightly too terse to be maximally useful, but nothing in it 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?

The presence of an output schema removes the need to explain return values, and the tool is simple (one param, no nesting). However, with no annotations and an entirely undocumented parameter, the description leaves gaps an agent must guess at regarding session_id validity and failure 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 0% for the single required session_id parameter, and the description says nothing about its format, where to obtain it, or whether it must reference an active session. The description therefore adds no meaning beyond the bare parameter name.

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 ("Return") and a specific resource ("state and prompt metadata for an active session"). It is distinguishable from siblings like open_session/close_session/terminal_read, though it never names them or contrasts its scope against read_output, which also returns data.

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 explicit when-to-use guidance, no prerequisites, and no mention of alternatives such as read_output or terminal_read. The phrase "for an active session" faintly implies it applies only to live sessions, but nothing tells the agent what to do with a closed or invalid session.

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 substantial work: it discloses blocking/quiet-detection behavior, timeout-driven termination, and that output includes pager screens, password prompts, banners and shell output with 'no prompt shape required.' It omits an important trait — whether reading consumes the buffer or is repeatable — plus any auth/permission requirements.

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?

Three tight sentences, each earning its place: behavior + termination condition, then return content, then sibling routing. Core semantics are front-loaded and there is 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?

An output schema exists, so return-value documentation is not required, and the description still usefully previews the content classes. Without annotations it should ideally cover buffer-consumption semantics and error behavior on invalid/expired sessions, which are the remaining 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 0%, so the description must compensate and it only partly does: it gives functional meaning to timeout ('until the stream is quiet or timeout expires'), but no units, no default (null), and no guidance on values. session_id gets no explanation at all, though it is self-evident from the sibling session tools.

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+resource (read terminal output) and adds the termination semantics ('until the stream is quiet or timeout expires'), which is more than a bare restatement. It partially distinguishes itself from siblings by naming read_output and session_status for offsets/buffered history, though the boundary between terminal_read and read_output remains somewhat blurred.

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 routes the agent elsewhere for a key need: 'Use session_status and read_output for offsets and buffered history.' That is a clear alternative pointer, but there is no when-not condition (e.g., when to prefer read_output entirely) and no prerequisite or auth guidance.

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 audit-logging of the full `data` string, the terminator behavior of `enter` including the serial carriage-return nuance, and the security constraint. It does not cover error behavior or whether writes block/fail on a dead session, so not a perfect 5.

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 core action, then progressively finer detail (use cases, terminator semantics, security). Every sentence adds distinct value with no repetition of the name or 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?

An output schema exists, so return values need not be described. For a 3-parameter write tool with no annotations, the description covers purpose, usage, key parameter behavior and the critical security caveat — nothing essential 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 coverage is 0%, so the description must compensate and largely does: it defines `data` as exact input that is audit-recorded and explains `enter` as appending the line terminator with a default implied. `session_id` is left to inference, which is reasonable given it appears across all sibling tools.

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 (write) and resource (session's terminal stream) with the exact-input semantics made explicit. It also names the sibling terminal_write_secret as the alternative for sensitive input, so an agent can differentiate it from the other session tools without opening schemas.

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 concrete positive guidance (commands, interactive keystrokes, nested hops like `ssh user@host`) and an explicit exclusion ('never type passwords, passphrases or other secrets here — use terminal_write_secret'), which is exactly the routing decision an agent needs.

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 that the value is resolved server-side and never appears in arguments, results, or audit, and that only the entry name and byte count are logged. It omits failure behavior, e.g. what happens if the session is not at a prompt or the entry does not exist.

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 rule, then the security/logging contract, in three tight sentences. The backtick markup on ``pass`` is slightly noisy 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?

An output schema exists, so return values need no explanation, and the security model is covered. What remains thin is error/precondition handling for a tool that types into a live prompt, plus the undocumented session_id.

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 0%, so the description must compensate. It clarifies that `entry` is a ``pass`` entry name whose value is resolved internally, which is genuinely useful, but `session_id` is never described beyond the implied "live" session context.

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 verb and resource (write a ``pass`` entry value into a live terminal prompt) and scopes it to secrets, which distinguishes it in spirit from the sibling terminal_write for non-secret input. It stops short of naming terminal_write as the alternative, so the differentiation is implied rather than explicit.

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 this for every secret typed interactively" gives a clear selection rule, reinforced with concrete prompt examples (device logins, ssh, enable, TACACS). It never states the inverse case (use terminal_write for non-secret text) or prerequisites such as an active session sitting at a prompt.

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