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

With destructiveHint=true and readOnlyHint=false, the safety profile is already known, and the description adds value by requiring verification of the candidate digest and approval note and by mandating real human approval control. It does not describe the destructive effect itself, but the annotations already flag it.

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 short sentences, each carrying a distinct constraint: human authorization, verification responsibility, and host-level control. Nothing is padded and the important restriction is front-loaded.

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 destructive approval action with no output schema, the description covers the critical safety and eligibility context. It omits the return value and exact effect of approval, but the name, annotations, and schema patterns cover enough for a cautious agent.

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 only hints at two of four parameters ('candidate summary' and 'approval note') and leaves taskId and expectedDigest semantics implicit. An agent needs to infer parameter roles from names and schema patterns.

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 the action and resource ('approve visual baseline') and adds a defining precondition: it may only run after explicit user review and authorization. It does not fully define what approving does to the baseline, but it is enough to distinguish the operation from read-only or preparation tools.

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 when-to-use conditions ('after user explicitly reviewed and authorized') and an explicit exclusion ('automated rework must not call'). It names no specific sibling alternative, so it stops short of the top score, but an agent can decide when the tool is appropriate.

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?

Adds substantial context beyond annotations: CLI agents kill the process tree while GUI agents best-effort click a stop button with a bounded timeout, and unconfirmed stops are surfaced in the result. This discloses mechanism, timeout bounds, and failure reporting for a destructive 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 dense sentence-cluster that front-loads mechanism (CLI/GUI) then state handling. Every clause carries information, though the GUI branch could be tightened slightly.

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 no output schema, the description usefully notes that unconfirmed stops are reported in the result. It covers destructive behavior and edge states well, but leaves the optional reason parameter unaddressed.

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 carry parameter meaning, but it mentions neither taskId nor reason. The purpose implies taskId identifies the target, yet the optional 'reason' parameter is entirely undocumented in both schema and 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?

States a specific verb (取消/cancel) and resource (任务/task), and goes further by defining behavior per task state (running, queued, terminal). An agent can immediately distinguish this from siblings like continue_task or rework_task.

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 state-based breakdown (running vs queued vs terminal) implies when the tool is appropriate, and 'no action for terminal tasks' warns of a no-op. However, it never explicitly names an alternative tool or states conditions for choosing cancel over verify_task/rework_task.

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 only give the safety profile (non-read-only, non-destructive, closed-world); the description goes further and discloses that message is routed to the original session in one case, is merely an acknowledgment in others, and is not sent at all under codex user_confirmation. That is genuinely useful behavioral context beyond the annotations, though it omits side effects like state transitions after resume.

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 purpose, then colon-delimited branches keyed to source (zcode/codex) and state. Dense but essentially waste-free; only the framework-specific jargon adds reading cost.

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?

No output schema and no parameter documentation exist, so the description bears the burden and largely meets it by enumerating the branch behaviors an agent must anticipate. It still leaves return values and failure handling unstated, which for a mutation tool is a modest gap.

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 carry parameter meaning, and it does for `message`: it is sent to the original session, downgraded to an ack, or not transmitted depending on source/state. `taskId` is never explicitly defined, but it is trivially inferable as the needs_user task identifier.

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 plus the gating state: '恢复处于 needs_user 的任务' (resume a task in needs_user state). That condition implicitly separates it from run_task/rework_task/verify_task, but no sibling is named outright, so it stops short of full 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 'needs_user' precondition is an implicit when-to-use rule, and the zcode/codex branches explain what happens per source state (agent_question, user_confirmation, login_required). However, it never names an alternative tool or states when NOT to use continue_task (e.g. for a task in another state, use run_task/rework_task 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?

Annotations already mark the tool as read-only and non-destructive, and the description is consistent with that. It adds useful behavioral context by disclosing that the output includes uninstalled/research placeholder hints and reflects the current state.

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 verb, and includes parenthetical detail about placeholder hints without padding.

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 no-parameter, read-only inspection tool with annotations covering safety, the description is nearly complete. It does not specify return format, but no output schema exists and the output content is summarized sufficiently for 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 tool has zero parameters and an empty schema, so there is no parameter semantics burden on the description. Per the baseline for 0-param tools, the description need not add parameter detail.

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 the verb '查看' and names a specific resource: current agent adaptation and executable detection results, including placeholder hints for uninstalled/research items. It is clearly distinct from the task-oriented sibling tools, though it does not explicitly name an alternative.

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 'use when' or 'instead of' statement. However, the description's focus on current agent profiles and the task-related sibling tool names make the intended usage reasonably inferable.

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 already declare readOnlyHint=true, so the description is not required to state safety. It adds the behavior of defaulting to the latest round when round is omitted, which is useful. However, it does not disclose anything about error conditions or what happens if no report exists for a round, but given the read-only nature and simplicity, a 3 is appropriate.

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, focused sentence that conveys the core action and the one non-obvious parameter behavior. No 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 simple read-only retrieval with annotations covering safety, the description covers the essential behavior (what it returns, round default). It does not describe the output format, but since there is no output schema, that would be nice, but the phrase 'full text (report.md)' gives a strong hint. Minor gaps remain, so a 4 is fair.

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 explains the round parameter's default behavior, which is valuable. taskId is not described, but its meaning is implied by the tool name and schema (string). It does not add syntax or format details, so a 3 reflects partial compensation.

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 the verb 'get' and the resource 'acceptance report' (report.md), and clarifies it's for a specific round. It does not explicitly differentiate from siblings like query_task or list_tasks, which could also return task-related data, so it loses a point for not naming an alternative.

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 on when to use this tool versus siblings. The description only mentions the round default behavior but does not state prerequisites, exclusions, or alternatives. An agent cannot infer when to prefer this over query_task or list_tasks.

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 already declare readOnlyHint=true and destructiveHint=false, so the read-only safety profile is covered. The description adds the historical scope and filter support, but does not disclose pagination behavior or whether the results are limited to certain statuses beyond the stated filters.

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 compact sentence that front-loads the verb and resource before optional filtering details. Every element earns its place and there is no redundant repetition of the tool name or title.

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 read-only list operation with no required parameters and no output schema, the description covers purpose, filters, and default limit. It does not describe the exact return shape, but the tool name and 'list tasks' phrasing make the core behavior sufficiently clear.

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 names all three parameters and their roles: projectPath and status are filters, and limit defaults to 50. This adds meaningful semantics beyond the bare schema, though it does not enumerate valid status values or projectPath formatting.

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 (列出/list) and resource (历史任务/historical tasks), and states the filter dimensions. This clearly distinguishes it from siblings like run_task, cancel_task, query_task, and get_task_report.

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 the tool by framing it as a way to list historical tasks with optional filters. However, it does not explicitly state when to prefer this over query_task or get_task_report, leaving some selection to inference.

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 already declare mutability and non-destructiveness, but the description adds that user authorization is required and that it returns a summary and preview. However, it does not disclose any side effects beyond not adopting the baseline, such as whether it reads or writes files, or affects task state. So it provides some context but not deep behavioral detail.

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 brief and to the point. The key information (purpose, non-adoption, auth requirement) is front-loaded. It does not include fluff. However, it could be slightly more structured to list parameters, but overall it is concise.

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 4 parameters and no parameter descriptions, the description is incomplete. It does not explain what each parameter is for, how they interact, or expectations (e.g., if projectPath is required, how to specify imports). The absence of output schema also means the description should clarify return structure, which it only vaguely does with 'summary and preview'.

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. The description does not explain any parameter semantics (e.g., what caseIds, imports, viewportIds mean). It only mentions 'prepare', which gives no parameter-level insight. This is a significant gap given 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 specific verb ('prepare') and resource ('visual baseline'), and clarifies it is a candidate, not a formal baseline. It distinguishes itself from sibling 'approve_visual_baseline' by indicating it is not adopting the baseline. However, it doesn't explicitly contrast with other siblings like 'get_task_report'.

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 implicitly conveys the purpose through 'candidate', but it does not provide explicit when-to-use guidance or mention alternatives. It lacks exclusions, e.g., when to use 'approve_visual_baseline' instead. The user authorization requirement is mentioned, which is a usage prerequisite.

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 already declare readOnlyHint=true and destructiveHint=false, and the description adds useful behavioral context: the default 40-line tail of agent.log and the returned data shape (task meta + log snippet). This goes beyond the annotations without contradicting them.

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 short sentences, front-loaded with the primary purpose and followed by the return format. Every clause adds information 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?

For a simple read-only tool with one required parameter and no output schema, the description supplies purpose, return contents, and a behavioral default. It is sufficient for an agent to call it correctly, though it does not mention error behavior or handling of very large tailLines.

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 carries the burden for explaining parameters. It implicitly clarifies tailLines via '默认 agent.log 末 40 行' and makes taskId's role obvious through '查询任务状态'. It does not fully enumerate constraints, but provides enough meaning for correct use.

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 '查询' (query) on the task resource and clearly enumerates what it provides: status, progress, recent log tail, task meta, and log snippet. It is specific and understandable, though it does not explicitly differentiate from siblings like get_task_report or list_tasks.

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 guidance about when to use this tool versus alternatives such as get_task_report or list_tasks. The read-only nature and log-tail focus imply a use case, but no exclusions or alternative routing are mentioned.

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 declare destructiveHint=true and readOnlyHint=false. The description adds meaningful context: it re-enqueues and continues, affects accounting, and advises on feedback content (include last failure summary). No contradiction with annotations.

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 compact sentence that front-loads the action and condition, then addresses the feedback parameter. No filler, every phrase 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?

Complete for a mutation tool without output schema. Covers what it does, when to use, and parameter guidance. Does not mention return value or side effects like task state changes, but that is not critical for a rework operation.

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 has 0% description coverage, so the description must compensate. It explains feedback as additional instructions with a suggestion, but taskId is left to the name and obviousness. Provides some added meaning but not full coverage for both parameters.

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 'rework' (re-enqueue) on a task resource, with an explicit condition: terminal states (failed/needs_attention). It also mentions same agent/project and round accounting, which differentiates it from generic run_task. No ambiguity or tautology.

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?

Clearly implies when to use: when a task is in failed/needs_attention terminal state and needs to continue. Does not explicitly name alternatives or exclusions, but the state condition is a strong usage signal that distinguishes it from running new tasks or querying.

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 already declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, indicating a mutating operation with side effects. The description adds context that the task runs externally, returns asynchronously, includes auto-acceptance/rework, and validates ZCode project path references before sending. This adds meaningful behavioral context beyond annotations, though it does not disclose failure modes or resource consumption.

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 compact, with the core purpose front-loaded in the first clause ('启动外部 AI-Agent 开发任务并可自动验收返修，异步返回 taskId'), followed by provider-specific details and a validation note. The structure is efficient with no redundancy, though it could be broken into clearer sentences for readability.

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 13 parameters and no output schema, the description is incomplete. It does not explain return value details beyond taskId, does not mention how to fetch results (e.g., via get_task_report), and leaves many parameter semantics unexplained. The provider-specific guidance helps but does not make the tool fully usable without additional documentation.

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 explains model and mode semantics for both providers (required vs optional, mode support), and mentions path validation for task/context. However, it leaves many parameters (autoVerify, autoFixRounds, taskTimeoutMs, reasoningLevel, allowCreateProject, planDoc, designSystem, agentId) undocumented, providing only partial compensation for the schema 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?

The description clearly states the tool launches external AI-Agent development tasks with auto-verification and rework, returning taskId asynchronously. The verb 'launch' plus resource 'external AI-Agent development task' makes the core action explicit. It does not explicitly differentiate from sibling tools like continue_task or rework_task, but the launch/dispatch nature is evident from the wording.

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 provider-specific guidance (ZCode vs TraeWork) for parameter values but does not explain when to use this tool versus alternatives such as continue_task or rework_task. There is no mention of prerequisites or conditions that would select this tool over a sibling, leaving tool-selection guidance entirely implicit.

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 already declare readOnlyHint=true and destructiveHint=false. The description adds '不改源码' (does not modify source code), reinforcing the read-only nature, and explains the check process (automatic commands + code analysis) and the ability to add extraChecks. This adds behavioral context beyond annotations without contradiction.

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 and front-loaded with the core purpose. It uses two sentences plus a requirement note, with no redundant phrasing. The key scoping (not modifying source) is placed early, and the parameter requirement is stated clearly.

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 5 parameters, no output schema, and no explicit sibling differentiation, the description is incomplete. It does not clarify the behavior of checksMode, the role of baselineRef, expected output format, or potential side effects beyond read-only. It leaves critical details for the agent to infer, which is risky for a verification 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?

With 0% schema description coverage, the description carries the burden for explaining parameters. It explains taskId/projectPath (must choose one) and extraChecks (temporary additions), but omits checksMode (append/replace) and baselineRef (git baseline). These are significant gaps that could lead to incorrect usage.

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 (perform acceptance check), the resource (completed task or project path), and the method (command checks + code analysis relative to git baseline). It distinguishes itself from siblings like run_task (execution) and get_task_report (report retrieval) by its focus on verification, though it does not explicitly name alternatives.

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 a usage context: for completed tasks or project paths, and requires a choice between taskId and projectPath. However, it does not explicitly state when to prefer this over siblings like get_task_report or rework_task, leaving some inference to the agent.

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