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 does indicate a non-mutating list operation and adds the useful behavior of surfacing sessions waiting for permission input. However, it does not disclose any potential side effects, permission requirements, or limits on the listing.

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 concise sentences with no filler. The primary action is front-loaded, and the additional detail about permission-waiting sessions is presented in a separate short sentence.

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 tool is simple and has no parameters or output schema, so the description is mostly sufficient. However, it does not state what the returned list contains (e.g., session IDs, statuses) which would be needed to use sibling tools like resume_copilot_session effectively.

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 correctly focuses on the output behavior rather than parameter details, which is appropriate since there is nothing to document.

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 ('List') and a specific resource ('available Copilot CLI sessions that can be resumed'), plus an additional behavioral detail about sessions waiting for permission input. This clearly distinguishes it from sibling tools that resume, run, or respond to 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 implies usage as a precursor to resuming sessions, but it never explicitly states 'use this before resume_copilot_session' or excludes the sibling tools. The context is reasonable but left to inference rather than explicit 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 provided, the description carries the full behavioral burden. It discloses the core action (sending user input to a waiting Copilot process) and the interactive-mode context, but it does not explain what happens after the response is sent, whether the session continues, or how the tool behaves if Copilot is not waiting for input.

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 sentences with the core purpose front-loaded in the first sentence, and the second sentence providing a concrete trigger example. There is minor redundancy between the two sentences (both mention permission), but no filler or wasted content.

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 2-parameter tool with complete schema coverage, the description covers the primary use case well. However, with no output schema and no annotations, it omits outcome details (what happens after the response is delivered) and edge-case behavior (failure when no process is waiting), which an agent would need for robust 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 100%, so the baseline is 3. The description reinforces the schema's response examples ('yes', 'no', or custom text) but adds no new parameter-level meaning beyond what the schema already documents for session_id and response.

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 action ('Respond to a Copilot CLI permission question') with a clear resource and context ('in interactive mode'), plus a concrete example ('Allow file modification?'). It distinguishes itself from siblings by framing the task as permission-response rather than session management, though it does not explicitly name any sibling.

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 an explicit trigger condition: 'When Copilot asks for permission... use this tool to send the user's response.' This tells an agent exactly when to invoke it. However, it does not explicitly address alternatives or exclusions, such as when to prefer resume_copilot_session or run_copilot_conversation instead.

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 burden. It discloses that the tool continues an existing conversation and accepts follow-up prompts, which is the core behavior. However, it doesn't mention side effects (e.g., whether resuming mutates the session, whether it consumes conversation turns, or whether it requires an active session). It also doesn't mention that cwd/model can override previous session settings, which is a behavioral nuance. The description is adequate but not rich.

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 sentences, front-loaded with the primary action and resource. The second sentence adds useful context about what resuming entails. No wasted words, though it could have used the space to mention overrides or exclusions.

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 6 parameters and no output schema, the description is somewhat thin. It doesn't explain what the response looks like, whether the session must be active, or how the overrides (cwd, model) interact with the previous session. The schema covers parameter syntax, but the description doesn't cover the operational context an agent needs to decide between this and run_copilot_conversation.

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

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

Schema description coverage is 100%, so the schema already documents all 6 parameters. The description adds the context that the prompt is a 'follow-up prompt or additional instructions' and that the session is resumed, which aligns with the schema. However, it doesn't add meaning beyond the schema for parameters like timeout_ms or permission_mode. Baseline 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 verb ('Resume'), the resource ('a previous Copilot CLI session'), and the mechanism ('by session ID'). It also explains what resuming does: 'continues an existing conversation with additional context or follow-up questions.' This distinguishes it from siblings like run_copilot_conversation (starting new) and list_copilot_sessions (listing).

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 this tool: when you have a previous session ID and want to continue it. It doesn't explicitly say 'use run_copilot_conversation for new sessions' or 'use list_copilot_sessions to find session IDs,' but the sibling names and the description's focus on resuming make the usage context reasonably clear. Missing explicit exclusions or alternatives.

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 openly discloses non-interactive mode and the needsInput=true possibility, which is useful. However, it does not warn that Copilot can execute shell commands or write files (given allow_tools and autonomous mode), so the tool could be misperceived as read-only.

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 wasted words. The core purpose is front-loaded, use cases follow, and the permission caveat is positioned at the end. Every sentence adds value.

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 no output schema and no annotations, the description is incomplete. It says 'returns the complete response' without specifying format (stdout/stderr/exit code) and omits side-effect warnings for a tool that can run arbitrary tools. Given the tool's complexity, more detail is warranted.

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

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

Schema coverage is 100%, so the structured schema already documents all parameters. The description adds some context around permission_mode behavior (interactive mode and needsInput), but does not materially enrich the meaning of the other parameters beyond what the schema provides.

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: 'Execute a prompt with GitHub Copilot CLI.' It clarifies the non-interactive mode (-p) and explicitly names respond_to_copilot as the sibling to use for permission questions, which distinguishes it from the other siblings.

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 tells the agent to use this for 'one-shot tasks like code generation, explanation, debugging, etc.' and provides a conditional alternative ('use respond_to_copilot to answer') for interactive permission mode. However, it does not explicitly mention when to prefer resume_copilot_session or list_copilot_sessions, leaving those exclusions implied.

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