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

No annotations are provided, so the description must carry the behavioral burden. It does disclose the key trait — output is the input returned unchanged ('原样回显'), and it is read-only with no side effects — but says nothing about error behavior for the required payload or any limits.

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 clause with the essential verb and qualifier front-loaded; nothing is padded. The '[MCP:demo]' prefix is a namespace marker rather than semantic content, a minor bit of noise.

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 one-string-parameter demo tool with no output schema and no annotations, the description covers enough: what it does, that it is read-only, and that the return is the input echoed back. Only edge-case behavior (empty or oversized payload) is left unstated.

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% ('payload' documented as '任意文本'), so the schema already explains the single parameter. The description adds no format, size, or content constraints beyond that, which is the expected baseline when the schema does the work.

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 concrete verb and object — '原样回显参数' (echo the parameters verbatim) — plus the qualifier '演示只读工具' (demo read-only tool). It is clearer than the bare name demo_echo, but it makes no attempt to differentiate from siblings (none of which overlap, so the omission is tolerable).

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 parenthetical '演示' (demo) implies this is a sample/testing tool rather than a production action, which weakly signals when to use it. There is no explicit when-to-use, when-not, or alternative named, so the guidance remains implied only.

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, and it does add one important trait: this write goes through policy/approval governance, so an agent can expect gating rather than an immediate effect. However it does not disclose what is mutated, whether it is reversible, what approval flow triggers, or what the result looks like.

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 short line with no filler, which is structurally fine, but the brevity comes at the cost of under-specification rather than being dense with useful information.

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 write tool with no annotations and no output schema, the description should explain the governance behavior, what the demo mutates, and what an agent gets back. It gestures at policy/approval but leaves the mechanics and the target of the write entirely unspecified.

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 both parameters (action, amount) are documented in the schema and the baseline is 3. The description adds nothing beyond the schema — it does not clarify the valid values for 'action' or what 'amount' governs, leaving '动作名' 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?

The description identifies the tool as a 'governed write action' and states it is a demo of how policy/approval applies to upstream tools, which conveys the general intent. But it never says what resource is being written to or what the action does, unlike siblings such as transfer_money or send_email which name a concrete operation. An agent knows it is a gated demo write, not what it operates on.

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 demo__demo_echo or the real write tools like transfer_money. The parenthetical implies it is illustrative, but the description never says to use it only for testing policy/approval flows or when to prefer the production equivalent.

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. It usefully discloses that the operation is read-only and includes retry behavior. However, it does not explain authentication requirements, failure semantics, retry limits, or what 'normalization' does to the returned data.

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 with no filler and front-loads the core purpose. The parenthetical adds useful behavioral context, though it compresses several ideas (read-only, retry) without elaboration.

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 annotations, no output schema, and a required parameter with 0% schema coverage, the description is too sparse. It does not describe the returned canonical fields, error behavior, or how invoice_id is interpreted.

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 required parameter, invoice_id, and schema description coverage is 0%. The description does not explain the expected invoice ID format, source system conventions, or lookup behavior. It leaves the only parameter entirely undocumented beyond its name.

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 and resource: querying invoices from ERP and normalizing them into canonical fields. Siblings are unrelated tools, so explicit sibling differentiation is less critical. It could be slightly clearer about whether it returns one invoice or many, since the name is singular but 'query' is broad.

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 any alternative, nor any prerequisites or exclusions. The only clue is '从 ERP' (from ERP), which implies data origin but not invocation conditions.

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. It implies a read-only listing but does not disclose recursion behavior, hidden-file handling, permissions, ordering, or error behavior.

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

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

The description is a single front-loaded sentence with little waste. The '[MCP:fs]' prefix is noise, but the core statement is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter listing tool with no output schema, the description is minimally adequate. It does not explain the return shape or listing behavior, but the core operation is understandable.

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 single path parameter is documented as 'Directory path relative to root'. The description adds no additional parameter semantics, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: list files and directories. It is clearly a listing operation, though it does not explicitly distinguish itself from the sibling fs__fs_read_file.

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 fs__fs_read_file. Usage is only implied by the word 'List', with no exclusions or context about when listing 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?

No annotations are provided, so the description carries the full burden. It implies a read-only operation but says nothing about encoding, binary files, size limits, path resolution relative to root, or what happens on a missing file — all material for a filesystem read.

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. It is appropriately sized, though its brevity comes partly at the cost of the missing behavioral detail noted elsewhere.

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?

A one-parameter read tool is simple enough that the definition is minimally viable, but with no output schema the description should at least indicate what is returned (raw text, error on binary) and confirm read-only safety, which it does not.

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 single parameter has 100% schema description coverage ("File path relative to root"), so the baseline is 3. The description adds no syntax, relative-path rules, or constraints beyond what the schema already states.

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 ("Read the contents of a file") with the "[MCP:fs]" namespace marker. An agent can distinguish it from fs__fs_list_directory by inference, but the description never names the sibling or contrasts the two 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?

No guidance on when to use this versus fs__fs_list_directory or other fs tools, and no preconditions such as the file needing to exist or being text vs binary. The only cue is the implied "if you need contents, read".

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 of behavioral disclosure and does not meet it: it does not say whether the call is read-only, whose calendar is returned, what time zone applies, or whether the result is empty when no events exist. Only the weak implication of "查看" (view) signals it is a read 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 phrase is front-loaded and contains no filler, which is structurally fine. The brevity here reflects under-specification rather than efficient communication, so it cannot earn a top score.

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 annotations and no output schema, the description is the only source of behavioral and return-shape information, and it supplies neither. For a one-parameter read tool the surface area is small, but an agent still lacks the date format and the identity of the calendar being read.

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 with 0% schema description coverage, and the description does not compensate by stating the date format (e.g. YYYY-MM-DD), time zone, or whether relative expressions are accepted. "某日" only echoes the parameter name at a conceptual level.

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?

"查看某日日程" gives a verb (查看) and a resource (某日日程), so the operation is identifiable as a read of one day's calendar. However, it never says whose calendar or what a "日程" entry contains, and the phrase is so terse that it barely rises above a title.

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 when-to-use guidance, no exclusion of alternatives, and no stated prerequisites. The sibling list (search_flights, get_weather, send_email, etc.) contains nothing comparable, so the agent gets no help at all in 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?

Because no annotations are provided, the description carries the full burden of behavioral disclosure, and it discloses almost nothing. The word '查询' implies a read-only retrieval, but the description says nothing about the data source, freshness, or whether the tool returns current conditions or a forecast. No behavior is contradicted; it is simply undisclosed.

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 definition is one short phrase with no filler and is fully front-loaded. However, the brevity reflects under-specification rather than disciplined conciseness, so it earns a middling score.

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 single-parameter tool with no output schema, an agent still needs to know the return shape, such as temperature units, returned fields, and current conditions versus forecast, plus any constraints on the city parameter. None of this information is present, so the definition is insufficient 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% for the single required parameter 'city', and the description adds no format guidance, such as city name versus city ID, or whether the parameter requires a Chinese or English name. The meaning of 'city' can be inferred from the parameter name alone, which raises the score above the floor but does not compensate for the documented 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 states a specific verb+resource: query city weather. That is clear, and because no sibling tool in the provided list overlaps with weather, no sibling differentiation is required. The description is clear but minimal; it does not say whether it returns the current weather or a forecast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool, when not to use it, or how it relates to alternatives. With no overlapping sibling tools, this omission is less harmful than it would otherwise be, but the description still leaves every usage decision 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?

No annotations are provided, so the description carries the full burden, yet it only discloses that credentials are injected by the gateway and are invisible to the agent. It does not disclose the salient side effect (interrupting a human), whether the call blocks, whether repeated pages are throttled, or what is returned. For an alerting mutation this is a substantial 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?

One compact sentence with the key constraint parenthesized immediately after the action, so nothing is buried. It earns its brevity, though the space saved is not reinvested in any operational detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no annotations, no output schema, and zero documented parameters, the description is too thin: the agent cannot tell when to invoke it, what to put in the message, or what happens on invocation. Only the auth-injection detail is complete.

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 required 'message' parameter is never explained. There is no guidance on what the message should contain (severity, service name, symptom, link), which is exactly what the description should compensate for at this coverage level.

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: page (呼叫) the on-call engineer. That is unambiguous and distinct from every sibling tool. It stops short of the top score because it offers no differentiation from notification-like siblings such as send_email, which an agent might reasonably choose instead.

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 never says when paging is appropriate: no urgency threshold, no escalation condition, no 'use send_email instead for non-urgent'. The agent must infer entirely from the tool name.

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 does disclose two behavioral facts beyond the name — the operation is read-only and the response includes per-field confidence. It says nothing about what happens on unparseable or partial input, error behavior, or which fields are extracted, so significant gaps remain.

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 clause with the action and the value-add (confidence) front-loaded; no filler. It is arguably too terse for what it omits, but nothing present 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?

For a one-parameter extraction tool with no annotations and no output schema, the description should at least indicate return shape and failure modes. It hints at per-field confidence but not at the field set or what an empty/failed parse looks like.

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 required string parameter with 0% schema description coverage, so the description must compensate. It implies the parameter is raw invoice text ('从非结构化文本'), which is useful, but adds no constraints on language, size, or expected encoding.

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: extract invoice elements from unstructured text, plus an output characteristic (per-field confidence). It is clearly a parsing tool, not a query tool like erp_query_invoice, though it never names that sibling or states the boundary 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?

There is no guidance on when to use this versus erp_query_invoice, no note on input prerequisites (language, format, length), and no exclusion of cases. The parenthetical '(只读)' is the only contextual hint and it is about safety, not selection.

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

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

No annotations are provided, so the description bears the full disclosure burden. It does add behavioral meaning by explaining that a higher risk_score means greater danger and that interpretation of the score is the responsibility of the governance layer. However, it says nothing about what happens when the payee is unknown, whether the lookup is a live or cached read, or what the returned fields look like.

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 core purpose front-loaded and no wasted text. The parenthetical clarification adds useful context without bloat.

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 has no annotations and no output schema, so the description should explain the return shape and the known failure modes. It only hints at the meaning of risk_score (higher = worse) and omits the score range, the response structure, and the behavior for an unrecognized payee.

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 the schema gap, but it adds nothing about the 'payee' parameter. It is unclear whether it expects an account number, a name, or an identifier, which is a meaningful gap for a required parameter.

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 ('查询收款方风险评分'), so an agent immediately knows it retrieves a risk score for a payee. It is not confused with any sibling, but it does not explicitly contrast itself with related tools such as transfer_money, which the agent might expect it to precede.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to call it: no mention of using it before transfer_money, no prerequisites, and no exclusions. The agent must infer the intended workflow entirely from the sibling list.

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 of disclosure. 'Search' implies a read-only operation, but the description says nothing about the data source, whether results include live pricing/availability, rate limits, or how results are ordered or paged.

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?

Extremely short and front-loaded with no wasted words, but this tips into under-specification. The single phrase does not carry enough information for a 3-required-parameter search tool.

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?

All three required parameters are documented in the schema, but there is no output schema and the description says nothing about what a search returns (flight list, prices, availability) or the one-way-only semantics implied by a single date field. For a search tool with no annotations and no output schema, this leaves meaningful gaps.

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% and each parameter has a clear description (date format YYYY-MM-DD, three-letter airport codes with examples), so the schema does the heavy lifting. The description contributes nothing beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('搜索航班' / search flights), which is unambiguous. Sibling tools are unrelated domains (invoice, calendar, weather, email), so no differentiation is required, but the description adds no scope detail such as one-way vs. round-trip or what is returned.

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 or when not to. There is no mention of prerequisites, whether dates must be in the future, or whether it handles multi-city/round-trip searches via the single 'date' parameter.

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 discloses nothing about side effects, irreversibility (sent mail cannot be recalled), rate limits, auth/from-address requirements, or delivery failure behavior.

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 short but only because it is empty; there is nothing to be front-loaded, and the four characters provide no information an agent could act on.

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 side-effecting tool with three required, undocumented parameters, no annotations, and no output schema, the description is completely inadequate.

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?

All three parameters (to, subject, body) have 0% schema description coverage and the description supplies no meaning: no format for `to` (single vs multiple, comma-separated, display names), no subject/body length or HTML/text expectations.

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 text "发送邮件" merely restates the tool name send_email; it names the resource and action but adds no distinguishing scope, recipient/format detail, or reason to prefer it.

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 when-to-use guidance, no prerequisites, no exclusions, and no reference to alternatives (none of the siblings send mail, but the agent is told nothing about that).

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, yet it discloses almost nothing beyond the name. For a funds-movement operation it says nothing about irreversibility, required permissions or authorization, amount limits, idempotency, or failure modes such as insufficient balance — only the outward direction is added.

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 text is a single five-character fragment rather than a concise description; it is under-specified rather than tight. There is no structure to front-load because there is essentially one phrase with no supporting detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A high-stakes mutation tool with zero annotations, no output schema, and partial parameter documentation requires a far richer description to be callable correctly. Nothing about confirmation, effects, or return behavior is present, so the definition is not sufficient for safe invocation.

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

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

Schema coverage is 33%: only `to` is documented ('收款方账号或邮箱'), while `amount` and `currency` have no descriptions anywhere. The tool description adds nothing about expected formats, currency defaults, or decimal/precision conventions, so the coverage gap is not compensated.

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 phrase '向外转账付款' names a verb (transfer/pay) and resource (money) and adds the direction ('outbound'), so the core action is identifiable. However, it is a bare fragment with no scope, no counterparty model, and nothing that separates it from the only related sibling, risk_check, which an agent would plausibly need to call first.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no when-to-use or when-not-to-use guidance and does not mention prerequisites, limits, or any alternative tool. An agent learns nothing about how this differs from risk_check or when a transfer should be preceded by a check.

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