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 the 50-item batch limit and automatic capacity pre-validation, but it does not cover failure semantics, duplicate handling, permission/auth needs, or whether the operation is atomic.

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

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

The description is three compact sentences: purpose first, then batch limit, then capacity-check behavior. Every sentence adds useful information without repetition or filler.

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

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

The schema is rich enough for parameters, and the description covers purpose and capacity validation. However, for a batch mutation tool with no annotations and no output schema, it omits important context such as partial-failure behavior and what happens to the created bookmarks.

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 schema has 100% description coverage, so both parameters are already well documented. The description adds only the batch limit and the requirement for a specific folder, not additional syntax or per-field meaning beyond the schema.

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: batch-adding multiple bookmarks to a specified folder. It also clearly distinguishes this from single-bookmark creation through '批量' and '多个书签', and the 50-item limit adds useful scope.

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

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

The description implies this is for creating multiple bookmarks at once and notes the 50-item cap, but it does not explicitly say when to use this instead of ilinks_create_bookmark or when not to use it. Usage is inferable but not fully guided.

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 key behavior: the setting is automatically verified and returns account and quota details, which signals a network side effect and the response content. It omits where the token is persisted and how invalid-token failures manifest, keeping it below a 5.

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, zero waste, with the action front-loaded and the usage condition and post-set behavior following in logical order.

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 2-parameter config tool with no output schema, the description covers what it does, when to call it, and what comes back (account and quota details). Only the persistence/error behavior is left unstated, which is a minor gap.

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

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

Schema coverage is 100%, so both `token` and `api_base` are already documented in the schema with defaults and sourcing hints. The description adds only indirect context via the environment-variable mention; it adds no new parameter-level meaning, 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+resource pair ('设置或切换 iLinks 认证 Token'), which is immediately distinguishable from the bookmark/folder CRUD siblings. It does not explicitly contrast with a sibling, but no sibling performs an auth operation, so ambiguity is minimal.

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 explicit trigger conditions: '若未配置环境变量或需要切换账号时使用' (when the env var is not configured, or when switching accounts). This is concrete context for invocation, though it does not state when NOT to use it (e.g., when a token is already configured and valid).

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 usefully discloses a quota pre-check and blocking behavior when the folder or staging box is full, which is valuable. It does not mention auth requirements, whether duplicate URLs are allowed, or what happens on success.

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 and compact, stating the action first and the quota behavior second. The second sentence is slightly verbose but every part earns its place by explaining the interception behavior.

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 mutation tool with no annotations and no output schema, the description covers the key quota blocking behavior and folder targeting. It still leaves gaps around permissions, duplicate handling, and post-creation response, so it is adequate but not 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 100%, so the schema already defines all five parameters. The description reinforces the folder vs. staging box behavior but adds no syntax or format details beyond what the schema provides, making the baseline 3 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 clearly states a specific verb and resource: adding a new bookmark to a specified folder or the staging box. It does not explicitly distinguish this single-create operation from the sibling tool ilinks_batch_create_bookmarks, keeping it from 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?

Usage is implied by '向指定文件夹或暂存箱添加新书签', which tells the agent this is for creating a single bookmark and that omitting the folder targets the staging box. However, there is no explicit guidance on when to use this tool versus ilinks_batch_create_bookmarks or ilinks_update_bookmark.

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 brunt. It usefully discloses a real behavioral trait beyond the schema: an automatic capacity pre-check that blocks creation at the folder limit. It omits other relevant traits for a mutation tool, such as permission requirements, name-uniqueness behavior, and what the password field enables on the public page.

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 and followed by the key behavioral caveat. Every sentence earns its place with no redundancy.

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 5-parameter mutation tool with no annotations and no output schema, the description covers the action and the limit-blocking behavior. It leaves gaps an agent would want: return value/created identifier, permission prerequisites, and how the optional password affects visibility.

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

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

Schema description coverage is 100%, so the schema already documents all five parameters including the bookmark/note enum and password semantics. The description adds no parameter-level meaning beyond the schema, which is acceptable at the baseline 3.

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 (创建新的书签或笔记文件夹) and even names the two folder subtypes, making the operation clear. It does not, however, distinguish itself from siblings like ilinks_create_bookmark, so an agent must infer the folder-vs-bookmark boundary.

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 plain 'create folder' statement, but there is no explicit when-to-use/when-not guidance and no routing to alternatives such as create_bookmark. The capacity pre-check note is behavioral rather than usage guidance.

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 usefully discloses the side effect that deletion immediately frees one bookmark quota slot, but it omits whether the deletion is permanent/irreversible, what permissions are needed, and what happens if the ID does not 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?

Two short sentences with zero waste; the deletion action is stated first and the quota consequence follows. Nothing is padded or redundant.

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 destructive tool with no output schema and no annotations, the description covers the action and its main side effect on quota, which is enough to call it correctly. The main remaining gap is the lack of any statement on irreversibility or error 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?

There is a single required parameter and schema description coverage is 100%, with the schema already documenting 'id' as '要删除的书签 ID'. The description restates this at the same level of detail without adding format or source hints (e.g., how to obtain the ID), so the baseline of 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?

The description states a specific verb and resource ('删除...书签') scoped to a given ID, so the agent can tell exactly what it does. It does not differentiate from siblings such as ilinks_move_to_temp or ilinks_delete_folder, which a stronger definition would name.

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 only implied: the tool deletes a bookmark, so it is used when a bookmark must be removed. There is no explicit when-to-use vs. when-not, and no mention of the alternative ilinks_move_to_temp that would apply if the user only wants to free quota temporarily.

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 at all, the description carries the full burden: it does convey destructiveness and the bookmark-content risk, which is valuable. It omits whether deletion is permanent, whether subfolders cascade, permission requirements, and response behavior — significant gaps for an unannotated mutation 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?

Two short sentences, action first then warning, with no wasted phrasing. Front-loading the deletion statement before the caveat is the right ordering.

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 destructive tool with no annotations and no output schema, the description covers the main hazard (contained bookmarks) but leaves unclear whether subfolders are affected and what a success response looks like. Adequate but with clear 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 the single 'id' parameter is fully documented in the schema as the folder ID to delete. The description only echoes 'the specified ID' without adding format or sourcing details, so 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 (删除...文件夹) scoped to a given ID, which cleanly separates it from ilinks_delete_bookmark and ilinks_create_folder. It does not explicitly name a sibling to contrast with, but the resource 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?

Provides a concrete precondition — confirm bookmarks under the folder are cleaned up or moved before deleting — which is exactly the context an agent needs before invoking a destructive operation. No alternative tool is named, so it stops short of a 5.

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

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

No annotations are provided, so the description carries the burden; it makes clear this is a pure query scoped to the current logged-in user and discloses the return contents (used, limit, remaining, VIP status), implying no side effects. It omits any note on auth prerequisites or rate limits, keeping it from a 5.

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

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

Two sentences, front-loaded with what is returned, followed by the actionable recommendation. 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?

With no output schema, the description usefully summarizes the return payload, so an agent knows what to expect. It does not clarify units (bookmark count vs. bytes) or whether VIP status affects the limits, minor gaps for a zero-parameter 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?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a parameterless tool 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 (查询) and resource (书签与文件夹容量配额) and enumerates the returned fields (已使用量、上限、剩余可用量、VIP 状态). An agent can distinguish this read-only quota check from the mutation siblings like ilinks_create_bookmark and ilinks_create_folder.

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 recommends calling it before adding bookmarks or folders, which gives a clear usage trigger. It does not name alternatives or state when not to bother (e.g., it is cheap/idempotent), so it falls short of full when/when-not guidance.

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 listing, but says nothing about result ordering, whether a total count is returned, permission requirements, or what happens with large result sets beyond the limit/offset params already in the 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?

Three short sentences, purpose front-loaded, the temp-box special case grouped with filtering. Nothing padded, though the pagination sentence largely echoes the 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?

For a simple, no-required-param read tool with full schema coverage and no output schema, the description covers the essentials. It still leaves open the default behavior with no folder_id, result ordering, and how it differs from the search sibling.

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 all three params are already documented, including folder_id=0 meaning temp box only. The description restates that same semantics without adding format or edge-case detail, 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?

The description names a specific verb and resource — viewing the current user's bookmark list — and scopes it to the caller's own bookmarks. It doesn't explicitly distinguish itself from the sibling ilinks_search_bookmarks, but 'list' vs 'search' is inferable from the wording.

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

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

It explains how to filter (by folder_id, or folder_id=0 for the temp box) which implies when to use each mode. However, it never states when to prefer this tool over ilinks_search_bookmarks, nor does it mention prerequisites such as being authenticated.

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 of behavioral disclosure. It implies a read-only list operation and documents the returned fields, but it does not mention permissions, pagination, or whether the result is complete versus bounded.

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

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

The description is compact and front-loaded: purpose first, returned fields second, and intended use case last. Every clause adds useful information without redundancy.

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 no-parameter list tool without an output schema or annotations, the description is largely complete: it explains what is returned and one key workflow. Missing details such as pagination or authorization requirements are minor given the tool's simplicity.

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

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

The tool has zero parameters, so there is no parameter semantics to clarify. The baseline score of 4 is appropriate for a no-parameter tool with fully covered schema.

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—'获取用户的所有文件夹列表'—and explicitly scopes it to all user folders. It also lists the returned fields, making it clearly distinguishable from sibling folder mutation tools like create_folder, update_folder, and delete_folder.

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 a clear use case: determining the target category folder before adding a bookmark. It does not explicitly state when not to use it or name alternatives, but the context is concrete and helpful.

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 add one genuinely useful behavioral fact — a capacity check on the temp box before the move, implying possible failure when full — but says nothing about auth, reversibility, or what happens if the ID is invalid or already in the temp box.

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 the action front-loaded and the precondition second. No filler, though the second sentence is slightly tangential to what the tool does.

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?

It is a single-parameter mutation with no annotations and no output schema, so the description should explain failure modes and result. The capacity precondition is a good start, but reversibility and error behavior for a bad ID remain undocumented.

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?

Only one parameter and schema description coverage is 100%, so the schema already documents 'id' as the bookmark ID. The description adds nothing beyond 'specified ID'; 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 (移入, move) and resource (书签, bookmark) plus the destination (暂存箱/uncategorized), which distinguishes it from siblings like ilinks_update_bookmark or ilinks_delete_bookmark. However it never contrasts itself with 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 only implied — the reader infers this is the way to un-categorize a single bookmark. There is no statement of when to prefer this over ilinks_update_bookmark or ilinks_delete_bookmark, and no note about batching (versus ilinks_batch_create_bookmarks).

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 never states that this is a read-only operation, whether results are capped or paginated, what the result ordering is, or that auth/quota (see ilinks_get_quota, ilinks_configure_auth) may apply — all real gaps for an unannotated 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?

One sentence, front-loaded with the verb and resource, with no filler. Every clause contributes information about what is searched and how matching works.

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 two-parameter search with full schema coverage the description is nearly sufficient. With no output schema and no annotations, however, it should say something about the shape or limit of returned results and confirm the read-only nature.

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%, so baseline is 3, but the description earns extra credit by explaining that the query is matched against multiple fields (name, URL, notes) rather than a single one — semantics the schema does not convey. It does not mention folder_id, though the schema documents that one adequately.

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 (搜索) and resource (用户已保存的书签), plus the matching scope (名称、URL、备注). It implicitly distinguishes itself from ilinks_list_bookmarks, but never names that sibling, so the differentiation is left to inference.

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 — call this when you have a keyword and want matching bookmarks — but there is no explicit when-to-use/when-not guidance and no pointer to ilinks_list_bookmarks for unfiltered browsing, despite a dozen siblings in the namespace.

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 says 'update' but does not disclose that four fields (id, folder_id, title, url) are required — implying a near-full replacement rather than a partial edit — nor does it mention permissions, reversibility, or 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?

A single front-loaded sentence with no waste, naming the resource first and then the affected fields. It is efficient but arguably too thin given the tool's mutation semantics.

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 mutation tool with no annotations and no output schema, the description omits update semantics (partial vs. full replacement given 4 required params), error behavior for invalid folder IDs, and the alternative for moving to trash. The schema covers parameter details, but behavioral context is largely absent.

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

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

Schema description coverage is 100%, so the schema already documents all six parameters including the folder_id caveat about 0 and ilinks_move_to_temp. The description only restates the field list at a high level and adds no syntax, constraints, or defaults beyond the schema.

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 (更新) and resource (书签) plus the field set it touches (标题、网址、所属文件夹、备注). This clearly separates it from create_bookmark and delete_bookmark, though it does not name 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?

There is no guidance on when to use this tool versus ilinks_create_bookmark, ilinks_move_to_temp, or ilinks_update_folder. The only routing hint ('若要移至暂存箱请使用 ilinks_move_to_temp') lives in the schema, not the description, and the description never mentions it.

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 at all, the description carries the full disclosure burden and does not meet it: it never says the operation mutates state destructively, whether the update is partial or requires resubmitting the full folder, what permissions are needed, or that the password field has clear-vs-noop ambiguity (only hinted at in the schema, not the description). Nothing beyond the bare 'modify' semantics is disclosed.

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 tight sentence with the action and affected fields front-loaded, and no filler. It is slightly under-specified rather than over-long, so conciseness itself is a strength here.

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 six-parameter mutation tool with no annotations and no output schema, this one-line description leaves critical gaps: the mandatory-name requirement versus the 'name, icon, description, or password' framing, the folder type enum, error behavior, and whether changes are reversible are all 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 100%, so all six parameters are already documented in the schema and the baseline applies. The description restates four of the fields but adds no semantics the schema lacks and never mentions content_type or the bookmark/note enum choice.

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-plus-resource ('修改现有文件夹' — modify an existing folder) and enumerates the mutable fields (name, icon, description, password), which differentiates it from ilinks_update_bookmark by target resource. However it omits the content_type field that the schema exposes, so the stated scope is narrower than what the tool can actually do.

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 pick this over siblings, no preconditions (folder must exist, must be owned/authorized), and no note that both id and name are mandatory — a real hazard given the description frames name as one of several optional things to change. The agent must infer everything about usage context 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.