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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds valuable context by noting that settings and YAML are reloaded from disk on every call, so edits take effect immediately. This reveals the tool's fresh-read behavior and implies it is non-mutating, though it does not explicitly state side-effect safety.

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 main purpose is front-loaded in the first sentence, and the second sentence adds a single, relevant behavioral note about reloading. Every word earns its place.

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 simple retrieval tool with no parameters and no output schema, the description covers the key points: what it returns and a notable behavioral characteristic. It does not specify the exact return format (e.g., JSON structure), but the mention of 'topology YAML' gives a hint. Overall, it is sufficiently complete for an agent to invoke 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?

The tool has zero parameters, so the baseline is 4. The description does not need to explain parameter semantics since none exist, and it correctly omits any param-related details.

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 specific verb 'Return' and the resource 'currently active lab topology', and explains what it contains (where work is performed, devices, links). It distinguishes itself from sibling tools like terminal operations by being the only topology-fetching tool, so an agent can easily identify its purpose.

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 it (when you need the active topology) but does not explicitly contrast with alternatives or state exclusions. Siblings are unrelated to topology, so the lack of explicit routing is less critical, but the guidance remains implicit 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?

With no annotations, the description carries the full burden, and it adds a meaningful behavioral detail: 'Reloaded from disk on every call,' indicating fresh data each invocation. The use of 'Return' also implies a read-only operation, though side effects, authorization, and error behavior are not explicitly disclosed.

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 fluff: it front-loads the returned content and adds the reload behavior in a single closing clause. Every word earns its place.

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-parameter, no-output-schema tool, the description is mostly complete: it names all three content areas and explains their purpose. It does not specify the exact structure of the returned data, but for this simple introspection tool that is a minor gap rather than a blocker.

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 has zero parameters, so the baseline is 4. The description focuses on what the call returns rather than parameters, which is appropriate for a parameterless retrieval tool.

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 ('Return') and names three concrete resources: operating principles, active scenario, and active reference knowledge. This makes the tool's purpose immediately clear and distinguishes it from terminal-focused siblings and get_active_topology.

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 'for the current task' conveys when to use this tool: when the agent needs behavioral guidance, task context, or reusable knowledge. It does not explicitly discuss alternatives or exclusions, but the sibling tools have clearly different functions, so usage context is reasonably 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?

With no annotations, the description carries the behavioral disclosure burden. It reveals non-obvious behavior: it only targets the production session namespaceĺ and deliberately works even when the device is absent from the active topology. It does not mention result/error behavior, but the key operational limits are disclosed.

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 sentences with no filler: the action is stated first, followed by a critical exclusion and a useful stale-session edge case. Slightly wordy in the third sentence, but every sentence contributes meaningful information.

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 tool with no output schema incl, the description covers target, scope, and an important edge case. It does not explain success/error responses or whether an open session must exist, but an agent can generally invoke the tool correctly with the provided information.

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 only parameter, device, is minimally described by the schema. The description clarifies that the device owns the session being closed, but it does not specify the identifier format or where to source it. With 0% schema coverage, this is only partial compensation, though reasonable for a single string parameter.

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: 'Close a device's managed production terminal session.' It also immediately distinguishes itself from related terminal tools by scoping to the production session namespace and explicitly stating it cannot affect validation sessions.

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: closing production terminal sessions, including stale sessions from before a topology change. It also states what it cannot do (affect validation sessions), which helps an agent avoid misusing it, though it does not explicitly name a sibling alternative.

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. It discloses important edge-case behavior: stale sessions remain visible and closeable, terminal_send()/terminal_read() will refuse them, and validation sessions are always excluded. This is substantial behavior disclosure, though it does not mention output format 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 front-loaded with the core action and then expands on meaningful edge cases. It is somewhat dense and long-winded, but each clause adds essential selection and invocation context, so the length is justified.

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-parameter listing tool with no output schema, the description is nearly complete: it defines what is included, what is excluded, and how results relate to sibling operations. It could be more complete by stating the return shape, but the core semantics are fully covered.

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 has zero parameters and an empty input schema, so there is no parameter semantics to clarify. The description correctly focuses on behavior rather than parameters, and the baseline of 4 applies because no argument documentation is needed.

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: 'List every currently managed production terminal session.' It clearly differentiates itself from get_active_topology by noting it includes sessions regardless of active topology, and from terminal_send/read/close by specifying stale sessions are closeable but not usable for I/O.

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 strong contextual cues: use it to see stale sessions and close them via terminal_close(), and it confirms local validation sessions are excluded. However, it never explicitly states when to choose this over get_active_topology or when not to use it, so the guidance remains implied rather than direct.

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 of disclosing behavior. It reveals that credentials are never returned, that topology is reloaded, that login prompts are auto-answered with private credentials, that it avoids jump hosts, and that it handles both SSH and Telnet. This is exceptionally transparent, leaving no critical ambiguity about what the tool does.

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 lengthy but each sentence adds essential detail about security, transport handling, and fallback behavior. The core purpose is front-loaded, and the complexity justifies the length. It avoids redundancy, though it could be slightly tightened without losing substance.

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 opening behavior, authentication, and fallback handling, but does not mention what the tool returns (e.g., a session identifier or status) and does not explain error conditions or what happens if the device is not found. With no output schema, this information is missing, leaving the agent uncertain about the tool's result.

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 single parameter 'device' has no schema description (0% coverage), and the description only says 'for a device in the active topology' without specifying how the device is identified (e.g., by name, ID, or IP). It does not add format or value guidance beyond what the schema already provides. Given the low schema coverage, the description should compensate but does not sufficiently clarify the parameter's semantics.

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: open or reuse a terminal session for a device in the active topology, launching ssh or telnet in tmux. It distinguishes itself from sibling tools like terminal_send and terminal_read by focusing on session opening rather than interactive I/O. The verb and resource are specific and 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 gives clear context on when to use this tool (to establish a session) and explicitly routes interactive prompts that the tool cannot safely resolve (host-key confirmations) to terminal_read()/terminal_send(). However, it does not explicitly state when not to use this tool, such as for simply sending a command without opening a session, though this is implied by sibling tool names.

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 burden of behavioral disclosure. It explicitly states that the device must be present in the active topology, that sessions are reloaded from disk on every call, and that an open session becomes unreadable if the topology changes. This is significant behavioral context that helps the agent avoid stale-state mistakes. However, it does not mention what happens if the device is not present (error type), nor whether this operation has side effects (it appears read-only, but not explicitly stated). Thus a 4, not 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?

The description is concise but packs significant information. It opens with a clear purpose statement, then details the 'lines' parameter, and ends with a critical caveat about topology. The sentences are purposeful and front-load the most important info. The caveat is placed at the end, which is acceptable. No filler. A 4 because it is slightly long and could be more concise, but each sentence earns its place.

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 tool's complexity (a read operation on a terminal session with a topology dependency), the description covers the key usage and behavioral aspects. It doesn't have an output schema, so it doesn't explain the return format, but that might be inferable. The description is complete enough for an agent to call it correctly: it knows the tool reads output, the 'lines' limit, and the topology dependency. The only missing piece is what happens when the device is absent, which could be inferred as an error. Thus a 4.

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 has 0% description coverage (no parameter descriptions in the schema), so the description must compensate. It explains the 'lines' parameter: 'limits how much recent scrollback is returned (default 100)'. It does not explain 'device' beyond the tool's purpose, but the purpose makes it clear that 'device' identifies which device's output to capture. This adds some meaning beyond the schema's raw type and default, but not exhaustive – e.g., no information about acceptable formats for device IDs. Thus a 3.

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: capturing recent terminal output for a device, and explicitly enumerates the kinds of output it can capture (prompt, command output, interactive prompts, paging, errors). This distinguishes it from sibling tools like terminal_send (which sends input) and terminal_open (which opens a session). The verb 'Capture' is specific and the resource is 'terminal output'.

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 guidance on when to use the tool: to inspect terminal output for a device during interactive sessions or after commands. It also gives a crucial exclusion: the device must be in the active topology, and the session does not remain readable if topology changes. This helps the agent choose this tool over alternatives like terminal_list (which lists sessions) and terminal_open (which creates a 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 provided, the description carries the full burden and excels at it. It discloses fixed execution order, no deduplication, that text bypasses argv and error messages, that the server does not log or echo input, and that tmux pipe-pane still records raw pane output. This is unusually transparent for a side-effecting 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 long but dense, with no filler. It front-loads the primary purpose and then adds necessary behavioral, ordering, and logging caveats. Every sentence earns its place.

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 prerequisites, ordering, logging, and privacy nuances almost completely. The only notable gap is return-value semantics: there is no output schema, and the description references 'tool result' only in passing without explaining what the agent receives on success.

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%, but the description compensates fully by explaining the semantics of device, text, keys, and enter, including ordering and the duplicate-Enter edge case. It adds meaning well beyond the bare parameter names in the input 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 states a specific verb and resource ('Send input to a device's open terminal session') and clearly differentiates the tool from siblings such as terminal_read, terminal_list, and terminal_open by focusing on sending input. It also narrows the scope to open sessions within the active topology.

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 provides strong operational context: the device must still be present in the active topology and the session is reloaded from disk on every call. However, it does not explicitly name sibling alternatives or state when not to use this tool, so the guidance is clear but not fully explicit.

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