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

No annotations are present, so the description carries the full burden. It reveals that the tool checks reachability and lists components, but it does not disclose potential side effects like booting the app-server (implied by 'after booting the app-server') or whether the operation is read-only. It also doesn't clarify the output format or error behavior, leaving gaps for a tool with no output 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?

Two sentences, tightly packed. The primary purpose and the key usage trigger are front-loaded, and every word adds value. 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?

Given the tool's simplicity (no parameters, no output schema), the description covers the core purpose and provides a usage trigger. It hints at the output content (binary path, credentials, models) but stops short of specifying the exact return shape. For a diagnostic tool, this is mostly complete, but a note on whether it starts the app-server or requires prerequisites would push it higher.

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 100% (vacuously). The description correctly omits parameter details, and the baseline for no-parameter tools is 4. It doesn't add misleading information, so a 4 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 uses a specific verb 'Report' and a clear resource 'zcode agent backend reachability', enumerating what is checked (binary path, stored credentials, available models). It distinguishes itself from siblings by positioning itself as a diagnostic for zcode_run failures, so an agent can tell it apart.

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 states when to use: 'Run this first when zcode_run fails.' This is a concrete trigger condition. It doesn't mention when not to use it or contrast with zcode_sessions, but the given condition is actionable and sufficient for basic routing.

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. It transparently discloses that zcode can read/edit files, run shell commands and git, and that it returns a response plus a session_id for follow-ups. It does not explicitly warn about autonomous state changes or side effects, but the description clearly indicates the agent operates inside the directory with file and command access.

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 three sentences with no fluff: purpose first, then capabilities, then return value and follow-up behavior. Every sentence adds information an agent needs, and the structure front-loads the core action.

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 7 parameters and no output schema, the description explains the key return format (final answer + session_id) and the operational context (works inside a directory, can modify files and run commands). It does not mention topics like authentication, cost, or failure modes, but the rich schema covers parameter details 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 description coverage is 100%, so the schema fully documents all 7 parameters. The description adds some useful context by linking 'given directory' to cwd and explaining that session_id supports follow-ups in the same conversation, but it does not meaningfully extend the schema's parameter documentation.

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 and resource: 'Delegate a development task to the zcode coding agent.' It clearly distinguishes this from sibling tools by describing what zcode_run does (running an agent) and what it returns (final answer + session_id), rather than checking or managing 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: when you need to delegate a development task to the zcode agent. It does not explicitly name alternatives like zcode_check or zcode_sessions or state when not to use this tool, but the run-vs-check/session distinction is strongly implied by the described behavior.

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 of behavioral disclosure. It says 'List recent zcode sessions' which implies a read-only, non-destructive operation, but it doesn't explicitly state that there are no side effects, no permissions required, or any rate limits. It does disclose the output fields, which is helpful, but lacks explicit behavioral detail for a listing operation.

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 sentence that is front-loaded with the primary purpose, followed by a direct tie-in to its output's use in zcode_run. No wasted words; every clause adds value. The structure is clean and immediately scannable by an agent.

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 there is no output schema, the description compensates by naming the returned fields (id, title, directory) and explaining how they are used (as session_id). It also mentions 'recent', implying a limited or time-ordered set, though it doesn't specify a count or ordering. For a simple list tool with one optional parameter, this is nearly complete; a note on whether it returns an array or object would push it to 5.

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%, and the cwd parameter has a clear description ('Workspace directory to list sessions for (default: server cwd)'). The tool description adds no additional meaning beyond what the schema already provides; it only reiterates the workspace context. Baseline 3 applies since the schema handles the parameter documentation.

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 (list), the resource (zcode sessions), and the returned fields (id, title, directory). It also notes the workspace scope, which distinguishes it from siblings like zcode_run (executes sessions) and zcode_check (presumably checks something else). This is 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 explicitly states that the output is usable as session_id in zcode_run, giving a concrete use case and linking it to a sibling. It implies this is the tool to call before running a session, but doesn't explicitly say when not to use it or mention alternative conditions. Clear context with no exclusions.

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