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

With no annotations, the description carries the full behavioral disclosure burden. It only says 'terminate and free resources' but does not mention that the operation is destructive, the effects of the 'kill' parameter, or any side effects on child processes. The description is too sparse to inform the agent of important behavioral traits.

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 a single concise sentence that is easy to parse. It is appropriately short, though it could be improved by front-loading more behavioral detail without becoming verbose.

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 tool, the description lacks key context: the meaning and impact of the kill parameter, the difference from tmux_close_session, and any side effects. Without these, the agent may invoke it incorrectly or struggle to choose between session tools.

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 only 50% (kill has a description, session_id does not). The tool description does not compensate by explaining either parameter. 'Terminate a session' implies session_id is the target, but the kill parameter semantics are left entirely to the schema's 'Defaults true' with no further 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 'Terminate a session and free resources' clearly states the verb (terminate) and resource (session). However, it does not distinguish this tool from the sibling tmux_close_session, so it misses the opportunity for differentiation.

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 guidance is provided on when to use this tool versus alternatives like tmux_close_session or how it fits into session management workflows. The description simply states the action without any context 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?

With no annotations provided, the description bears full responsibility for disclosing behavioral implications. 'List active sessions' only states the action and object, offering no detail on return format, pagination, filtering, side effects, or permission requirements. It adds no behavioral context beyond what the tool name implies.

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 a single, short sentence with no wasted words, making it concise. It does, however, border on under-specification by providing only 'active' as a qualifier, but for a simple list tool it is efficient and not overly verbose.

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?

Despite the tool's simplicity, the description lacks important context given the sibling tool 'tmux_list_sessions'. It does not clarify whether 'sessions' refers to tmux sessions or others, nor does it explain what 'active' means or what the output includes. With no output schema, the description alone is insufficient to fully understand the tool's scope.

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 the schema coverage is trivially 100%. Per the scoring guidelines, 0 params warrants a baseline of 4. The description correctly adds nothing about parameters because there is nothing to explain; it does not mislead or omit necessary parameter information.

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 'List active sessions' clearly states the verb 'list' and the resource 'active sessions', making the core purpose understandable. However, it does not distinguish this tool from the sibling 'tmux_list_sessions', which could also list sessions, creating ambiguity. Thus it lacks sibling differentiation.

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 no guidance on when to use this tool versus alternatives like 'tmux_list_sessions' or 'open_session'. There is no mention of context, prerequisites, or exclusions. It merely states the function without any usage direction.

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 must carry the burden. It does disclose that the session is stateful and uses a PTY by default, and that it returns a session ID. However, it omits behavioral details such as whether the subprocess runs continuously, how output is buffered, and whether the session requires explicit termination.

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 one sentence, immediately front-loads the core action, and contains zero filler. Every word adds value: 'stateful,' 'subprocess,' 'PTY by default,' 'returns a session id.'

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 tool that spawns a persistent process with six parameters and no annotations or output schema, a single sentence is insufficient. It doesn't explain the session lifecycle (e.g., use send/read to interact, close_session to terminate), parameter interactions, or error conditions. The description leaves critical context to the user to discover.

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 only 33% (pty and max_buffer_bytes have descriptions), requiring the description to compensate. The description adds little beyond what the schema already says; it does not explain cwd, env, args, or command semantics. The only param hint is 'PTY by default,' which duplicates the schema's pty 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?

The description clearly states a specific action (spawn), resource (stateful subprocess session), and key detail (PTY by default). It distinguishes from sibling tools like tmux_open_session (which targets tmux sessions) and run (which likely executes a one-off command) by emphasizing the stateful session and returned session ID.

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 no guidance on when to use this tool versus alternatives like tmux_open_session for tmux workflows or run for quick commands. It does not mention prerequisites, lifecycle management (e.g., needing to close the session), 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?

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It only says 'accumulated output' without explaining drain semantics, blocking behavior, timeouts, or ANSI handling. These behaviors are implied by the parameters but not described in prose.

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 a single sentence that immediately states the function. It is appropriately brief and front-loaded with the key verb and object, with no filler or repetition.

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?

This is a read operation with 5 parameters, no output schema, and no annotations. The description does not explain return format, buffer behavior, blocking/timeout behavior, or how it relates to open_session/close_session. For such a nuanced tool, the description is too minimal to be fully actionable.

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 description coverage is 60%, with drain and strip_ansi having descriptions, but max_bytes, session_id, and timeout_ms lack descriptions. The tool description adds no parameter semantics beyond what the schema provides, leaving three parameters unexplained. It does not compensate for the coverage gaps.

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 'Read' and a clear resource ('accumulated output from a session'), which distinguishes it from sibling tools that send or run. However, 'accumulated output' is somewhat vague and could benefit from specifying whether it's terminal output or something else.

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 no guidance on when to use this tool versus alternatives like send or run. It does not mention prerequisites, typical scenarios, or when not to use it. The single sentence offers no context for 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?

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It mentions the idle condition but does not explain side effects, blocking behavior, error cases, or what happens with timeouts and byte limits. The description is too sparse for a tool with 10 parameters.

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 a single sentence that front-loads the 'Convenience' label and immediately states the core behavior. Every word adds value, and there is no redundant information. It is efficient and easy to parse.

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 has 10 parameters, no output schema, and no annotations, the description is severely under-specified. It does not explain what the function returns, how it handles session state, or the meaning of 'idle' beyond the parameter name. The convenience wrapper concept is clear, but the operational details are 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 70%, which provides baseline semantics for most parameters. The description adds context for the overall workflow (send then read until idle) but does not clarify the remaining undocumented parameters like strip_ansi or append_newline. It neither over-compensates nor contradicts 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?

The description states a clear verb and resource: 'send a command then read until output is idle.' This distinguishes it from sibling tools like send and read, as it combines both actions in a convenience wrapper. The resource (command) is explicit, and the behavior is specific.

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 labels the tool as 'Convenience,' implying it is an alternative to manually calling send and read together. However, it does not explicitly state when to use it instead of those siblings, nor does it mention any exclusions or alternative use cases. This is implied 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?

Annotations are absent, so the description carries full responsibility for behavioral disclosure, but it only states the basic action. It doesn't mention newline handling, blocking behavior, or effects on the session, leaving the agent uninformed about important operational traits.

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 a single, concise sentence that is immediately understandable. It avoids unnecessary words and front-loads the key action, though it sacrifices detail for brevity.

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 three parameters, no output schema, and no annotations, the description is too sparse to provide adequate context. It doesn't explain prerequisites (e.g., must have an open session), how the session_id is obtained, or how append_newline affects behavior, leaving significant gaps for an agent to safely invoke the tool.

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 low (33%), with only append_newline having any description. The tool description adds no meaning for data or session_id, and does not clarify how raw input is transmitted or what format data should take. The description fails to compensate for the schema's sparsity.

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 ('send') and resource ('session's stdin'), clearly conveying the tool's function. It distinguishes from siblings like 'run' or 'tmux_send_keys' by specifying raw input to a session's stdin, though it doesn't explicitly contrast with them.

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 guidance is provided on when to use this tool versus alternatives like 'run' or 'tmux_send_keys'. The description simply states what it does without any contextual usage instructions 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?

No annotations are present, so the description carries the full burden of behavioral disclosure. It does not mention key behaviors such as line range handling (start_line, end_line), ANSI inclusion/stripping, or whether the capture is read-only. The phrase 'as text' hints at output format but fails to disclose how parameters affect the result.

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 a single concise sentence with no wasted words. However, it is so terse that it borders on under-specification, though this is not a padding issue.

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 7 parameters, no annotations, and no output schema, a one-sentence description is insufficient. It does not explain the capture scope (e.g., which pane, what the current pane refers to), line range options, or the meaning of the return value. The tool requires more context 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?

Schema description coverage is 86% (high), so the baseline is 3. The description adds no parameter-level meaning beyond what the schema already provides, so it neither helps nor hurts.

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?

Clear verb+resource: 'Capture the current pane contents as text' explicitly states what the tool does and distinguishes it from siblings like send/read. The output type (text) is also specified.

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 guidance is provided on when to use this tool versus alternatives like send or read. The description is a single declarative sentence with no context for selecting this tool over others.

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 the action is destructive ('Kill') and limited to sessions created by this server, but does not explain side effects (e.g., whether attached clients are disconnected, if data is lost, or if the operation is irreversible). This is thin for a destructive 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 a single sentence, front-loaded with the action and target, and contains no wasted words. It is concise, though it could benefit from a bit more detail without losing conciseness.

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 one-parameter tool, the description is minimally adequate, but the destructive nature and lack of annotations or output schema mean more context is needed. The description does not explain return values, error handling, or prerequisites, making it incomplete for safe 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 schema has a single required parameter 'session_id' with no description, and the tool description offers no explanation of what this ID represents or its format. With 0% schema description coverage, the description must compensate, but it does not address the parameter at all.

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 action ('Kill') and the resource ('a tmux session created by this server'), which distinguishes it from generic session operations. The phrase 'created by this server' narrows the scope. However, it does not explicitly differentiate from the sibling 'close_session', leaving some ambiguity.

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 the tool is for killing tmux sessions but provides no explicit guidance on when to use it versus alternatives like 'close_session' or 'open_session'. No exclusions or prerequisites are mentioned, so the agent gets minimal context for selecting this tool over others.

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 exist, so the description carries the full burden. It implies a read-only operation by stating 'List active tmux sessions', but does not provide details such as the exact output structure, whether it returns session IDs or names, or any potential side effects. The phrase 'created by this server' adds some scope context, but key behavioral aspects remain unspecified.

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 a single, focused sentence that is front-loaded and contains no extraneous information. It perfectly balances brevity with 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 tool's simplicity (no parameters), the description is mostly sufficient. However, the absence of an output schema means the description should have indicated what the response looks like (e.g., session names, IDs, status). Without that, the agent must infer the return format. Also, no guidance on when to use this versus sibling tools reduces completeness.

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 schema is trivially covered at 100%. Per the baseline for 0-param tools, a score of 4 is appropriate. The description adds contextual meaning by specifying that only active sessions created by this server are listed, but there are no parameters to describe.

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 identifies the tool as listing active tmux sessions specifically created by this server, using a specific verb ('List') and resource ('tmux sessions'). The qualifier 'created by this server' differentiates it from the sibling 'list_sessions' tool, which likely covers sessions from other sources.

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 guidance is provided on when to use this tool versus alternatives like 'list_sessions' or other tmux-related tools. The description only states what it does, without any context on use cases 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?

With no annotations, the description carries the full burden. It reveals that the session is detached and returns an ID, which is valuable, but it omits details like session naming, error behavior, or whether the command runs interactively. It also doesn't clarify what 'running a command' implies for PTY handling.

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 a single, well-structured sentence with a clear order: action, use case, return value. Every clause earns its place, and there is no redundancy or irrelevant detail.

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?

Despite having 6 parameters, nested objects, and several closely named siblings, the description is minimal. It does not explain how to use the returned session ID for subsequent interactions, nor does it distinguish this tool from open_session or run, leaving significant gaps for a moderately complex tool.

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 only 33% (width/height described), yet the description adds no explanation for cwd, env, args, or command. 'running a command' only hints at the command param, leaving the other 4 params entirely unexplained. This does not compensate for the low schema coverage.

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 function: 'Start a detached tmux session running a command' and mentions a use case (TUI apps) and return value. However, it does not explicitly differentiate from sibling 'open_session', relying on the tmux prefix in the name.

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 a clear use case ('useful for full-screen TUI apps like vim/htop') but lacks explicit when-not-to-use guidance or alternatives. It does not mention when to prefer this over 'open_session' or 'run'.

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 must carry the full burden of behavioral disclosure. It only says 'Resize a tmux session window' and gives no details about side effects, units (pixels/cells), persistence, or how the session is affected. This adds no information beyond the tool's name.

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 a single, front-loaded sentence with no fluff, which is efficient. However, it is so brief that it borders on under-specification, providing only the fundamental action without essential supporting details.

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 no annotations, no output schema, and zero parameter coverage, the description is grossly insufficient. It lacks any context on return values, side effects, or parameter behavior, making it impossible for an agent to use the tool correctly without external 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?

Schema description coverage is 0%, and the description does not mention any of the three parameters. There is no explanation of what width, height, or session_id mean, their units, or constraints. The description completely fails to compensate for the lack of schema descriptions.

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 clear action ('Resize') and resource ('tmux session window'), which distinguishes it from sibling tools that open, close, send, or list sessions. However, 'session window' is slightly ambiguous—it could refer to the terminal window or the tmux window pane—so it is not perfectly specific.

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 guidance on when to use this tool versus alternatives, nor any mention of prerequisites, exclusions, or typical scenarios. The description only states what it does, leaving the agent to infer usage context entirely.

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 burden of behavioral disclosure. It adds that keys are sent to the 'active pane' and that tmux-style key tokens are supported, but does not mention errors, edge cases, or the effect of the 'enter' or 'literal' flags beyond the schema.

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 one sentence, front-loaded with the action and target, and includes helpful examples. Every word contributes value; it is concise without being under-specified.

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 tool with a clear schema, the description is adequate but incomplete. It lacks guidance on when to use it versus alternatives and does not describe the result or behavior for non-existent sessions, though the schema covers 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 coverage is 75% with clear descriptions for keys, enter, and literal. The description adds examples of key tokens but does not add significant meaning beyond the schema, so the baseline of 3 applies.

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 verb 'Send' and the resource 'key tokens to a tmux session's active pane', and includes concrete examples (Enter, Escape, C-c). This distinguishes it from sibling tools like tmux_capture_pane or tmux_resize.

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 intended use is implied: use this when you need to send key tokens to a tmux session. However, it does not explicitly contrast with alternatives like 'send' or mention when not to use it, so it lacks clear 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 bears full responsibility for behavioral disclosure. It discloses the sequence (send, wait, capture), the timing behavior ('wait briefly'), and the output ('pane snapshot'), plus the roundtrip efficiency. It does not cover error behavior or side effects beyond sending keys, but for the core behavior it is quite transparent.

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 a single, information-dense sentence. It front-loads the action ('Send keys') and efficiently packages the three-step process and use case without any wasted words.

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 tool with 11 parameters and no output schema, the description provides essential context: it is a combined send-and-capture step for TUI interaction, with a roundtrip purpose. The rich schema covers parameter details, so the description doesn't need to explain them. It could mention prerequisites or error scenarios, but the core functionality is adequately conveyed.

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 91%, so the schema already documents the parameters thoroughly. The description adds minimal semantic value beyond implying 'keys' and 'delay_ms', but it does not need to repeat schema details. A baseline of 3 is appropriate.

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 function: send keys, wait for redraw, and return a pane snapshot. This identifies it as a composite operation and distinguishes it from siblings like tmux_send_keys or tmux_capture_pane, which handle only one part.

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 'one roundtrip for TUIs' gives clear context for when to use this tool: when you need to send input and immediately capture the redrawn pane, especially for terminal UI interactions. It implies the advantage over separate send and capture calls but does not explicitly name alternatives or exclusions.

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