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

With no annotations supplied, the description carries the full burden and does well: it discloses that the default is destructive-but-reversible, that `permanent=True` is unrecoverable, and a non-obvious edge case (items already in the trash are hard-deleted regardless). It does not mention auth/permission requirements or rate limits, which is the remaining gap for a mutation tool with zero annotation coverage.

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 tight sentences plus a short caveat note. The default mode is front-loaded, the irreversible mode follows, and the edge case is separated out — no filler or repetition.

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

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

The tool is simple (2 params, one required), an output schema exists so return values need no explanation, and the description covers the destructive-mode semantics well. The only shortfall is the undocumented `id` parameter, which leaves a small hole in an otherwise complete definition.

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 fully explains the `permanent` flag's semantics and default behavior, but says nothing about the required `id` parameter — an agent gets no confirmation that this is a message identifier rather than a folder or account id. Partial compensation only.

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 ('删除邮件') and immediately splits the operation into two modes: default soft delete (moves to trash) versus `permanent=True` hard delete. This distinguishes it adequately from siblings like `move_email` and `mark_email`, but it never explicitly names those siblings as alternatives, so the differentiation is implicit rather than stated.

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 clear conditions for choosing each mode: omit `permanent` for reversible removal, set `permanent=True` for irreversible deletion, and it explicitly recommends client-side manual confirmation before doing so. It also warns that deleting a message already in the trash bypasses soft delete entirely. What it lacks is any mention of sibling tools (e.g. using `move_email` when a plain trash move is intended).

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 and does disclose the important traits: this writes files to disk, content is never returned inline, and there is a default output directory. It omits other behavior an agent would want — overwrite behavior for existing files, whether the id must be a specific email, and what happens when a keyword matches multiple attachments.

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 tight clauses with the primary behavior and the non-inlining guarantee front-loaded, followed by parameter defaults. No filler; only the lack of visual separation between the two parameter clauses slightly reduces scannability.

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 no explanation, and the description covers the side effect, defaults, and argument forms. The remaining gap is error/edge-case behavior (keyword matching multiple attachments, existing-file overwrite) for a tool that writes to disk.

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 it does for two of three parameters: attachment (blank=all, 1-based index, or filename keyword) and save_dir (blank defaults to ~/Downloads/email-mcp/<account>/). The id parameter is left unexplained, though its meaning is inferable from the sibling tool set.

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 opens with a specific verb+resource: save email attachments to local disk and return a list of paths, plus the key distinguishing note that attachment content is never inlined in the response — which separates it from get_email. It does not name a sibling tool explicitly, so it lands just 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?

It gives clear selection semantics for the attachment argument (blank = all, 1-based index, or filename keyword) and the default save location, which tells an agent how to call it. However, there is no explicit when-to-use/when-not guidance relative to get_email or search_emails, so the routing decision is left 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?

With no annotations, the description carries the full burden and handles it reasonably: it discloses the default 2000-character truncation, the special body_max=0 behavior, and that attachments are returned as metadata only. It leaves unstated whether fetching marks the message as read and any error or permission 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?

Three short sentences, front-loaded with what is returned before the parameter notes; every clause carries information. Slightly dense Chinese phrasing with parenthetical asides, but no wasted wording.

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 two-parameter read tool with an output schema already covering return shape and no annotations, the description is nearly complete: return components, truncation, and the body_max escape hatch are all stated. The remaining gap is read-side effects on message state, which an agent might reasonably wonder about.

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 supply meaning and it does: body_max's default, its zero-value semantics, and how to read the full text are all explained, and id's provenance is given. What's missing is any note on id format or whether the default truncation can be exceeded in one call.

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 gives a specific verb+resource (读取邮件详情) and enumerates exactly what is returned: headers, plain-text body, attachment list with metadata only. It partially distinguishes itself from siblings by noting attachments are metadata-only (implying get_attachments for content) and that the id originates from search_emails, though it never names an alternative tool outright.

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 how to control body retrieval (body_max=0 skips the body, larger values fetch more) and where the id comes from (search_emails), which is concrete usage context. It does not state when NOT to use this tool or explicitly route attachment downloading to get_attachments.

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 must carry the full behavioral burden; it usefully discloses the empty-return case and that the return value contains further guidance. It does not state that the call is read-only with no side effects, nor whether it requires any local or auth setup, so an agent cannot fully characterize the behavior from the description alone.

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 short sentences, with no wasted words: first what the tool lists and its fields, then the edge-case behavior. The core purpose is front-loaded and the caveat follows it.

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 description need not explain return values, and it correctly focuses on the one edge case (empty result means uninitialized). For a zero-param discovery tool, this is nearly complete; only the absence of read-only and side-effect reassurance keeps it from a 5.

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

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

The tool takes zero parameters, so there is no parameter semantics to obscure; the baseline 4 applies. The mention of returned fields is a bonus that helps interpret the result, though the output schema already covers that.

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 gives a specific verb and resource ('列出已配置的邮件账户') and names the fields returned (id, 登录用户, IMAP 服务器), so the agent knows exactly what this tool surfaces. It doesn't explicitly distinguish itself from the sibling email tools, but those all operate on folders or messages, so there is no real ambiguity.

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?

For an agent looking for configured accounts, usage is implied, and the note about empty results and initialization provides some practical guidance. However, it never states when to call this tool versus the sibling tools, for example, that it is a discovery step before list_folders or search_emails, and it does not state 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?

No annotations are provided, so the description carries the full burden; it discloses the concrete output format and, importantly, the non-obvious fallback behavior that a blank account auto-selects when exactly one account exists. It stops short of stating whether the call is read-only or what happens when multiple accounts exist and account is omitted.

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: the first front-loads the resource and the per-line output template, the second covers the single edge case. No filler or repetition of schema fields.

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?

Output schema exists, so return values needn't be explained, and the description still adds the human-readable line format. Behavior for the only parameter is covered for the single-account case; the multi-account, blank-argument case is the one gap remaining for a tool this simple.

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% and the single account param has no title or description in the schema, but the description supplies the essential semantic: leave it blank and a sole account is chosen automatically. The remaining ambiguity — how to choose among multiple accounts — is not addressed, so it falls short of full 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 a specific verb and resource (列出账户的 IMAP 文件夹) plus the exact output shape '名称 (N封/M未读)', which tells an agent precisely what comes back. It is distinguishable from list_accounts and search_emails by the folder-oriented scope, though it never names those siblings 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 by the resource: use this to enumerate folders and their counts. There is no explicit when-to-use rule, no mention of what tool to call first (e.g. list_accounts) or when to prefer search_emails, so an 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?

No annotations are supplied, so the description carries the full behavioral burden for a mutation tool. It discloses the "at least one flag" constraint but says nothing about permissions required, idempotency/reversibility of the flag change, whether unmentioned flags are left untouched, or whether side effects (notifications, sync) occur.

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 short clauses plus a constraint sentence, flag semantics front-loaded, zero filler. Every element earns its place and the constraint is stated last, which is the natural reading order for the reader.

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. For a 3-parameter mutation tool with no annotations, though, the description omits the identity/scope of `id` (single message vs batch) and any safety context, leaving the definition only partially sufficient to call 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?

Schema description coverage is 0%, so the description must compensate. It does explain the boolean semantics of `read` and `starred` (True/False meaning) plus the at-least-one rule — real added value beyond the bare titles. But the required `id` parameter is left unexplained: no indication whether it is a single message ID, a comma-separated list, or an ID format, leaving a critical 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 uses a specific verb+resource ("标记邮件" / mark email) and immediately enumerates the two flag dimensions it can change (read/unread, starred/unstarred), which is far more concrete than the bare tool name. It does not name any sibling for comparison, but none of the siblings (move_email, delete_email, get_email) overlap with this purpose, so ambiguity is low.

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?

"至少传一个" gives a real usage constraint (at least one of read/starred must be supplied), which is genuinely needed since the schema marks only `id` as required and both flags default to null. However, there is no guidance on when to prefer marking over move_email/delete_email workflows, nor on whether repeated calls are safe or what happens if both flags are omitted.

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 does not meet it. It does not say what happens if the folder does not exist, whether the folder is auto-created, what permissions are required, or whether the move is reversible. Only the implicit 'move = removed from source folder' semantics can be inferred from the verb.

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 short sentences, front-loaded with the core action, and the parenthetical archive note earns its place by resolving a likely ambiguity. No filler, though the terse mixed-language phrasing is marginally harder to parse than a single consistent sentence.

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

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

An output schema exists, so return values need no explanation, and with only two required parameters the surface area is small. Still, the definition leaves the 'id' parameter and failure/folder-existence behavior undefined, which matters for a destructive-ish mutation with no annotations.

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 does well for to_folder by explaining that names come from list_folders and defining the archive convention, but the required 'id' parameter is never explained (message ID? thread ID?). Half the parameters remain semantically opaque.

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 ('move email') plus the destination concept (a folder), which is clearly distinguishable from siblings like delete_email or mark_email. It also clarifies the 'archive' case. It stops short of naming sibling tools to contrast with, so it sits at 4 rather than 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?

It gives one useful prerequisite: to_folder values must come from list_folders. However, it offers no guidance on when to move versus mark or delete an email, and no explicit when-not-to-use conditions. Usage is implied rather than stated.

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 supplied, the description carries the full burden and does a good job: it discloses the no-body/token-saving behavior, the exact output line format, sort order (newest first), and a performance caveat that text search is slower. It omits read-only confirmation and any rate/volume limits tied to the limit parameter, so it is strong but not complete.

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 purpose and return shape before parameter notes, and every clause carries information without padding. The telegraphic style is dense but readable; a little more structure around the parameter notes would improve scanning.

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 an 8-parameter tool with 0% schema coverage and no annotations, the description should cover more of the surface area; limit, folder, account, and unread_only are silent gaps that can cause wrong calls (e.g. searching only INBOX by default). The presence of an output schema means return values need not be spelled out, yet it helpfully does so anyway.

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% across 8 parameters, so the description must compensate. It explains field values (subject/from/to/text), the since/before 'YYYY-MM-DD' format, and empty-query behavior, but leaves limit, folder, account, and unread_only completely 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?

The description gives a specific verb plus resource (搜索邮件) and immediately fixes the scope: compact metadata only, no body, token-saving. It also states the exact record shape returned (id | date | sender | subject [flags]), which makes it clearly distinct from get_email, the sibling that returns full content.

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 establishes concrete usage contexts: field=text for full-text including body but slower, and empty query with no dates to list everything newest-first. It also implies the follow-up path by saying returned ids are passed to get_email/mark_email/move_email/delete_email/send_email. It doesn't explicitly say when to prefer get_email over this tool, so it falls short of full when/when-not coverage.

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 supplied, the description carries the full burden and does well: it discloses that draft=True suppresses sending, that reply/forward auto-populate headers, recipients, quoting, and empty subject/body, and that original attachments are NOT copied. It omits what happens if in_reply_to and forward_of are both passed (error vs silent precedence) and says nothing about the account parameter's resolution or auth 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?

Purpose is front-loaded in the first clause, followed by tightly ordered parameter guidance, the mutual-exclusion constraint, and the auto-fill fallback. Every line carries information, though the telegraphic '。'-separated fragments are dense and would read slightly better as structured bullets.

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 10-parameter mutation tool with zero annotations, the description covers send-vs-draft semantics, reply/forward composition rules, attachment handling, and parameter conflicts. An output schema exists so return values need not be described; the remaining gap is the undocumented 'account' parameter and unstated error behavior on conflicting inputs.

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 it does for 9 of 10 parameters: address formats for to/cc (string, list, or 'Name <a@b>'), meaning of draft, reply_all, in_reply_to, forward_of, attachments, and the auto-fill behavior for subject/body. Only 'account' is left completely unexplained.

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 opens with a specific verb+resource ('发送邮件') and immediately names its key variant behavior (draft=True stores a draft instead of sending). It also references the sibling get_attachments in the forwarding flow, so the agent can position this tool among list_accounts/search_emails/get_attachments without opening the schema.

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 explicitly states when to use draft mode, when to pass in_reply_to versus forward_of, that the two are mutually exclusive, and that forwarding does not carry attachments automatically — instead the agent should call get_attachments first and pass results via attachments. That is a concrete when-to-use plus when-not-to-use (mutual exclusion) and an alternative-tool handoff.

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