openaaas-mcp-adapter

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

No annotations are provided, so the description carries the full behavioral burden, and it says almost nothing. It does not disclose whether cancellation is idempotent, what happens to already-completed tasks, whether in-flight work or artifacts are discarded, or what permissions/auth are needed 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?

The single short sentence is front-loaded and wastes no words, but that brevity is under-specification rather than efficiency. There is no structure to speak of for a mutating tool with an undocumented parameter surface.

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?

An output schema exists, so return values need not be described, but everything else is missing. With no annotations and 0% parameter coverage, the definition leaves a destructive operation's scope, preconditions, and failures entirely unexplained.

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% for two parameters, and the description never mentions either. The required task_id is undocumented (format, where to obtain it, e.g. from submit_task), and the 'server' parameter with its default empty string is entirely unexplained, leaving the agent to infer its meaning.

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 (取消/cancel) and resource (任务/task) and narrows scope to tasks that are currently executing, which separates it from submit_task or get_task in a general sense. It does not explicitly name or contrast those siblings, so it stops short of a 5.

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 only usage signal is the implicit restriction '执行中的' (executing), which hints that completed or pending tasks are out of scope. There is no statement of when to prefer cancel_task over alternatives like poll_task, no prerequisites, and no guidance on what to do if cancellation fails.

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 behavioral burden, and it discloses almost nothing: no mention of network access, whether authentication is required, whether the call mutates server-side state, or what happens on an unreachable URL. The presence of an output schema covers return values, but the operational profile of the call remains entirely undocumented.

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 short sentence with no waste, which is appropriate in size, but the brevity comes at the cost of information rather than through efficient compression. There is no front-loaded explanation of what an agent gets back or what the parameter needs.

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 output schema relieves the description of explaining return values, but for a discovery tool that requires a URL argument and has no annotations, the description should at minimum state what is discovered and what form the server_url must take. Neither is present, so an agent would be guessing on first 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 0% for the single required server_url parameter, and the description never mentions the parameter at all — no expected format, scheme, trailing-slash conventions, or whether it must be a configured server. The description fails to compensate 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?

"发现服务端 API 信息" states a verb (discover) and a resource (server-side API information), but "API information" is vague — it doesn't say whether it fetches a discovery document, a capability list, or metadata. It also doesn't distinguish itself from siblings like list_servers or list_services, which arguably overlap in intent.

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 statement of when to call this versus alternatives such as set_server_url, list_servers, or register. An agent cannot tell whether discovery must precede registration or whether it is a read-only probe, so usage must be inferred from the tool name alone.

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 useful behavior about default file selection and returned paths, including a warning not to guess subdirectories, but it does not mention save location, overwrite behavior, permissions, or other side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the main action, then uses concise bullets for parameter behavior and a short warning about paths. Every sentence adds useful information without waste.

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?

An output schema exists, so return-value details are less necessary, and the description still explains returned paths. However, with no annotations and incomplete parameter coverage, it should do more to explain the server parameter, required task_id semantics, and when this tool is preferred over siblings.

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 documents file_id and download_all well, but task_id is only implied and the server parameter is entirely undocumented.

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: downloading task result files and returning each file's full path. It is clear what the tool does, but it does not differentiate itself from siblings such as list_files or get_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?

It explains default file selection and download_all behavior, which gives implied usage. However, it does not say when to use this tool instead of list_files or get_task, nor does it state any exclusions or prerequisites.

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 but does disclose the nature of the payload (capability scope, invocation rules, return format, limits), which is meaningful content beyond the schema. However it says nothing about whether the lookup is read-only, what happens for an unknown service_id, or whether usage docs are static or server-specific.

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 front-loaded sentence with a parenthetical inventory of what the docs contain — no waste. It is, if anything, slightly terse for a two-parameter tool with an output schema.

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 existence of an output schema excuses explaining return values, and the description covers the documentation's content well. But for a tool with zero schema coverage on two parameters and no annotations, it leaves the `server` parameter and error behavior 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 compensate and largely does not. '指定服务' gestures at service_id, but the `server` parameter (defaulted, empty string) is entirely unexplained in both schema and description, leaving a required and an optional parameter underdocumented.

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 ('获取指定服务的详细用法说明') and enumerates what the returned documentation covers (capability scope, invocation conventions, return format, limitations). This clearly separates it from siblings like list_services, which only enumerate services. It stops short of 5 only because it doesn't name an alternative explicitly.

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?

Usage is implied — an agent should call this when it needs to know how to invoke a particular service — but there is no explicit when/when-not statement and no reference to sibling tools such as discover or list_services. The agent must infer the workflow position.

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 present, the description carries the full burden. It usefully discloses that this is a read/query-only tool and adds a strong anti-polling constraint, but says nothing about cost, latency, or what happens when the task is still running versus finished.

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?

Short and front-loaded, but the 'only call when the user explicitly asks' instruction appears twice — once in the parenthetical and again in the warning — with no added information the second time.

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?

An output schema exists, so return values need not be described. However, with zero annotation coverage and zero parameter documentation, the description leaves the agent without any indication of which task_id/format is valid or how to handle a still-pending task.

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 both parameters (task_id, server) are undocumented in structured data and the description adds nothing about them. It does not explain what task_id refers to or how the optional server parameter affects lookup.

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 and resource: query task status and final result. It is distinguishable from submit_task/cancel_task, and the warning implicitly contrasts with poll_task, though that sibling is never named.

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?

Gives an explicit trigger ('only when the user explicitly requests') and an explicit exclusion ('do not poll proactively'), which is exactly the guidance agents most often get wrong on task tools. It stops short of naming poll_task as the alternative, so routing is implied rather than directed.

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. It does not say whether listing requires the task to be finished, whether paths are returned for later download, whether the listing is paginated, or what happens if no files exist.

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?

One short, front-loaded sentence with no filler, but it is under-specified rather than genuinely concise. It reads as a label more than a usable instruction.

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?

Though an output schema exists and the description need not explain return values, the tool still lacks annotation coverage and has two undocumented parameters. For a task-scoped listing it omits when it applies, what it returns conceptually, and how 'server' selection works.

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 implies task_id is the key input but says nothing about the format of the ID, and the 'server' parameter — its default behavior, and how it interacts with set_default_server — is entirely unaddressed 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?

The description states a specific verb and resource: list the result files belonging to a task. An agent can tell this is a read-style listing of task outputs, though it never distinguishes it from neighbors such as download_result or list_services.

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 call this versus download_result (fetch contents) or get_task, and no stated prerequisites such as whether the task must be completed first. Usage is only implied by the phrase 'result files'.

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 behavioral burden but only says 'list all configured servers'. It does not disclose whether unreachable or disabled servers are included, whether the result is paginated, or what the read-only nature implies beyond the 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?

A single, front-loaded sentence with no waste, well matched to a zero-parameter tool. It is perhaps too terse to earn a 5.

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 output schema documents return values and there are no parameters, so the remaining gap is small. Still, the description could clarify whether only currently configured servers are returned.

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 takes zero parameters, so there is nothing for the description to disambiguate. The baseline of 4 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 names a specific verb (list) and resource (servers), scoped to "configured" servers, which distinguishes it from discover. However, it does not differentiate from the sibling list_services, which reads similarly.

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 indication of when to call this versus discover or list_services, and no prerequisites or exclusions are stated. The agent must infer usage from the name alone.

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 behavioral burden. The phrase 'lightweight summary' hints at the return shape, but there is no disclosure of read-only nature, authentication/server resolution behavior, pagination, or what happens with the server parameter.

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 single short phrase is front-loaded and wastes no words, but its brevity reflects under-specification rather than disciplined conciseness given the undocumented parameter and absent usage guidance.

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?

An output schema exists, so return values needn't be explained, but with no annotations and an entirely undocumented 'server' parameter, the definition leaves meaningful gaps for an agent trying to call it correctly.

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

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

There is one parameter, 'server', with 0% schema description coverage, and the description never mentions it. The agent gets no information about what the parameter filters or what the empty default means.

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: retrieve the list of available Agent services, with a note that it returns a lightweight summary. However, it does not distinguish it from siblings like list_servers, discover, or get_service_usage, which an agent could easily confuse it with.

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 such as discover or list_servers, nor any exclusions or prerequisites. The agent is left to infer usage entirely from the name and sibling context.

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 disclosure burden well: it names the polling interval, the default unbounded timeout, the terminal states, and the strong agent-side restriction on invocation. It does not say what is returned when timeout_seconds expires, which is the one remaining behavioral gap.

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 and functional, but the 'only when user explicitly asks' rule is stated twice (in the parenthetical title line and again in the ⚠️ block, restated in both Chinese and English), which is redundant space.

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?

An output schema exists, so return values need not be described. The blocking/polling behavior and invocation guardrails are covered; only the 'server' parameter's meaning and the post-timeout outcome are left open.

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 clarifies timeout_seconds (caps total polling duration, default null = no limit), but says nothing about the 'server' parameter, leaving the target-server selection ambiguous.

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 and resource — polling a task until it reaches a terminal state — and adds the distinguishing behavioral detail (20s interval, completed/failed/cancelled). This is clearly separable from siblings like get_task (single check) and cancel_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?

Explicitly says when to use (user explicitly asks to wait/poll, with example utterances) and when not to (agent must not call proactively; ask the user instead). No inference required.

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 must carry the behavioral load: it does disclose that registration is a one-time action and yields an api_key, which is real context beyond structured fields. It is silent on what happens on repeat invocation (new key vs. error), whether credentials are required to register, and whether existing state is overwritten — significant gaps for an account-mutating 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?

A single front-loaded clause with the verb first and zero filler; nothing is wasted. It is lean to the point of under-specification, but the phrasing itself is efficient and well-structured.

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?

An output schema exists so return formatting need not be explained, but with no annotations, 0% param coverage, and a required 'name' input left unexplained, the definition does not give the agent enough to invoke the tool correctly on the first try. It needs to cover the parameters and repeat-call behavior.

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 mentions neither parameter, so the agent gets no information on what 'name' represents (client name? account identifier?) or what 'server' is for (target endpoint? default empty means what?). The only semantic hint is the output (api_key), which does not compensate for two fully undocumented inputs.

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 (注册 / register) and resource (客户端账号 / client account) and names the concrete outcome (获取 api_key), so the agent knows it is an account provisioning tool rather than a general auth call. It does not explicitly contrast with siblings such as update_profile or discover, but the purpose itself is 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?

'仅需一次' (only needed once) is a genuine usage hint that this is one-time setup, implying it should be called before other operations. However, it never states prerequisites, whether it must precede discover/submit_task, or what to do if a key already exists — the when-to-use signal 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?

With no annotations, the description carries full burden; it does disclose that the operation destroys configuration and includes a guard against deleting the default server. It omits reversibility, effect on running tasks/services bound to that server, permission requirements, and failure behavior, which are material 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?

A single short sentence that front-loads the action and appends the key constraint in parentheses. Nothing is wasted.

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?

An output schema exists, so return value explanation is not needed, and the core destructive action plus one guard is covered. But for a destructive tool with no annotations and an undocumented parameter, the description should also address identifier format and side effects on running services to be fully sufficient.

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% for the single 'server' parameter, so the description must compensate and it does not: it never states whether the identifier is a name, URL, ID, or index, nor whether it must match an entry from list_servers. An agent could easily pass the wrong identifier format.

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+resource ('删除指定服务器的配置' – delete the specified server's configuration), which is unambiguous and distinguishable from siblings like list_servers or set_default_server. It does not explicitly contrast itself with those siblings, but the destructive action is clear on its own.

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 supplies one important 'when-not' condition (the default server cannot be deleted), which is real usage guidance. However, no alternative path is offered (e.g., use set_default_server first) and no preconditions like required permissions or server-state 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?

No annotations are provided, so the description carries the full burden, yet it says nothing about persistence, scope of effect (global vs. session), or what happens if the named server does not exist. Only the bare implication of a state change is conveyed.

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 one-phrase description is front-loaded and wastes no words, but its brevity reflects under-specification rather than discipline — nothing substantive is delivered in the short space.

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?

An output schema exists, so return values need not be described, but with zero annotations and zero parameter documentation for a state-changing tool, the definition leaves too much for the agent to infer before calling it.

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 single parameter "server" is left unexplained — it is unclear whether it expects a server name, ID, or URL, or whether it must match an entry from list_servers. The description does nothing to compensate for this 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?

"切换默认服务器" states a specific verb (switch) and resource (default server), so the operation is unambiguous. It does not, however, distinguish itself from the sibling set_server_url, which sounds like it also modifies which server is used.

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 versus set_server_url, list_servers, or register. No prerequisites (e.g., must the server already be registered?) or exclusions are given.

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 supplied, so the description carries the full burden. It does disclose the key side effect — the value is written to a config file, making the change persistent — which is genuinely useful. But it says nothing about whether an existing entry is overwritten, whether the default server is affected, or what validation occurs on the URL.

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 with the write-and-persist behavior front-loaded and no filler. It is efficient, though its brevity edges into under-specification given the undocumented parameters.

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 config-mutating tool with a declared output schema but zero annotation coverage and 0% parameter documentation, the description leaves too much open. The unexplained 'server' parameter and the unaddressed overlap with set_default_server are gaps an agent must guess through.

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 and does not. It references the server address, which maps to the required server_url, but the second parameter 'server' (defaulting to empty string) is never mentioned and remains entirely opaque — an agent cannot tell how it relates to server_url.

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 and resource: set the server address and save it to the configuration file. The persistence is explicit, so the action is distinguishable from a pure in-memory setter. It does not, however, distinguish itself from the sibling set_default_server or explain how the two differ.

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 versus set_default_server, list_servers, remove_server, or the 'server' parameter. The agent must infer the selection criteria from the sibling names alone.

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, so the description carries the full burden. It does disclose meaningful operational constraints (files must be under the current working directory, 100MB per-file cap), which is real value, but it omits whether submission is async, whether it returns a task id to poll, and any auth/service requirements.

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 compact sentences, front-loaded with the core action followed by the file-upload constraint. No filler, though the constraint is scoped only to one parameter.

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 6-parameter async-style submission tool with zero schema coverage and no annotations, the description is too thin: it explains one parameter's constraints but not session reuse, service selection, or expected flow (submit → poll). The output schema covers return values, but the invocation contract is largely unexplained.

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% for 6 parameters, so the description must compensate. It only explains input_files; server, service_id, session_id, task_prompt, and output_prompt remain entirely undocumented, leaving the agent to guess at the most important required fields.

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: submit a task to a remote Agent, with the extra capability of file upload. It is distinguishable from the read/cancel siblings (get_task, poll_task, cancel_task) by the 'submit' action, though it never explicitly contrasts 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 on when to use this versus poll_task/get_task or when a new submission is warranted versus continuing a session_id. Only a constraint on file inputs is given, not usage context.

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 disclosure burden, yet it says nothing about permissions required, whether the rename persists server-side, what happens to already-issued tokens or sessions, or whether the change is reversible. For a mutation tool with zero annotation coverage this is a substantial gap, only partly offset by the presence of an 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?

It is a single front-loaded sentence with no filler, which is structurally sound, but the brevity crosses into under-specification rather than economy. Nothing is wasted, yet very little is delivered.

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 an output schema present the return shape need not be described, but for a two-parameter mutation with no annotations the definition leaves key calling questions unanswered — the meaning of 'server', the scope of 'current client', and the effect of the rename. It is not complete enough for confident 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 0%, so the description must compensate for both parameters, but it mentions neither explicitly. In particular the optional 'server' parameter (default "") is never explained — an agent cannot tell whether it namespaces the profile, targets a remote server, or is irrelevant here.

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 and resource, 修改 (modify) + 用户名 (username), and scopes it to the current client (当前客户端). An agent can tell this is a profile mutation and not a server/task operation, though it does not explicitly contrast itself with the server-management siblings. It is clear but not differentiated.

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 statement of when to call this versus alternatives such as set_default_server or register, and no prerequisites or exclusions are given. The agent must infer usage entirely from the one-line purpose.

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