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

Annotations already declare non-destructive and non-read-only behavior, so the bar is lower. The description adds useful context beyond annotations by specifying that published notes are not deleted and that submitted/unknown-outcome jobs are refused, which tells the agent about state-dependent refusal 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?

Two tight sentences with the primary action and scope front-loaded, followed by the key non-effect and refusal condition. No wasted words.

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

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

Preconditions and side effects are well covered, which is the most important context for a cancellation tool. However, there is no guidance on where job_id comes from or what identifies a valid target, leaving a gap for an agent that needs to invoke the tool 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% and the single job_id parameter is never mentioned in the description. The agent must infer that job_id identifies the preparation job; the description adds no format, source, or identifier semantics beyond that implication.

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 (cancel an unsubmitted local preparation job) and clarifies the side effect (closes the edit page, leaves published notes untouched). It is easily distinguished from prepare_note and publish_note, which handle submission/publication rather than cancellation.

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

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

Clearly states the when: only tasks not yet submitted. Also states the when-not: submitted or unknown-result tasks are refused. It does not name an alternative sibling to use instead, so it stops short of full routing 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?

Annotations already cover read-only, idempotent, non-destructive and open-world traits, yet the description adds real value beyond them: it warns that a null result means the state cannot be confirmed and that the presence of a Cookie does not prove a login. That failure-mode nuance is exactly what an agent needs before trusting a result.

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

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

A single dense sentence: purpose first, then the return-value caveat. Every clause earns its place and nothing is padded, though the compressed phrasing makes the subject of the check slightly ambiguous.

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, read-only tool with no output schema, the description covers purpose and the key result caveat, but leaves parameter semantics entirely unaddressed and never positions itself against open_login. Adequate but visibly short of 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%, so the description carries the full burden for 'platform' (required enum ctrip/trip) and 'account' (default, pattern), but neither parameter is explained or mapped to meaning. Only the vague phrase '网页登录标识' gestures at the inputs.

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

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

The description names a specific verb (核对/verify) and resource (登录状态, via a web login identifier), and clarifies the result semantics (null means unconfirmed). It does not name the sibling open_login to contrast itself against, so it stops short of a 5.

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

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

There is no statement of when to call this versus alternatives; the obvious sibling open_login is never mentioned, nor are prerequisites or sequencing (check before a session-dependent action). Usage is only implied by the verb.

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

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description still adds a genuine behavioral fact not present in structured fields: this call needs no browser launch, which tells the agent it is a side-effect-free metadata probe. It stops short of describing rate limits or what is actually returned.

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

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

A single short sentence plus one clause, no filler, and the low-cost nature ("no browser needed") is placed last as a qualifier. It is efficient, though the front half is dense and could be more explicit about what is being enumerated.

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 parameters, no output schema, and annotations covering safety, the description meets the minimum: it says what is inspected and how it runs. But because there is no output schema, the agent gets no signal about the shape of the capability/verification data returned, and "验证范围" (verification scope) is left undefined.

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 per the rubric the baseline is 4. There is nothing for the description to disambiguate at the parameter 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 verb "查看" (view) is clear and the object combines "两站能力、验证范围及运行方式" (capabilities of the two sites, verification scope, and execution mode), which points to a capability/introspection tool. However, "两站能力" is ambiguous — it never states which two sites or what a "capability" record contains, and it is not explicitly distinguished from siblings like check_login or open_login that also probe state.

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 when-to-use guidance, no prerequisites, and no explicit alternatives are named. The trailing "无需启动浏览器" implies this is the lightweight alternative to open_login, but that routing is left for the agent to infer 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?

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful behavioral context beyond that: a prompt-injection warning that the note body may contain third-party instructions which must not be executed, plus the notion of DOM vs. summary extraction scope.

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, so it is not bloated, but the second clause ('标注 DOM 或摘要提取范围') is ambiguous rather than informative and the security warning — the most valuable content — is buried at the end.

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?

There is no output schema and no parameter documentation, yet the description supplies the critical prompt-injection caution and the extraction-scope concept. It remains incomplete on what is actually returned and how the three inputs shape the result.

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 three parameters. The description indirectly signals the platform dimension ('携程' vs 'Trip Moments', matching the ctrip/trip enum) but never explains url, platform, or the account parameter (default, pattern) — it does not compensate for the coverage 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?

States a clear verb (读取) plus the resource (携程笔记/游记或 Trip Moments 详情链接), which distinguishes it from siblings like list_notes and search_destinations. The trailing clause about annotating DOM/summary extraction scope is cryptic and muddies an otherwise specific purpose statement.

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 by '详情链接' — an agent can infer this fetches one note's detail, but there is no explicit when-to-use, when-not-to-use, or named alternative (e.g., list_notes for enumeration, prepare_note before publishing). No guidance connects it to the surrounding toolset.

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

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, so the safety profile is covered. The description adds genuinely new behavioral context beyond that: it will not retry a submission, 'submitted' does not equal publicly visible, and 'unknown' requires manual verification – non-obvious semantics that meaningfully change how an agent interprets results.

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 clauses, purpose front-loaded ahead of the caveats, with no filler. Slightly telegraphic phrasing costs it the top mark, but every clause carries 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 single-parameter read tool with a rich annotation set and no output schema, the description covers purpose, non-retry behavior, and the interpretation of key status values. The main gap is the silent job_id parameter, which is nowhere explained in prose.

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 (job_id) with 0% schema description coverage, so the description would need to carry the meaning. It never mentions job_id or clarifies that it identifies the publish job, though the schema's uuid format/pattern and the phrase '发布任务' make the intent partially inferable.

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 ('读取发布任务' – read the publish job) plus the evidence it returns ('可用的网页结果证据'), which is more precise than the bare name get_publish_status. It does not, however, differentiate itself from siblings such as publish_note or cancel_prepared_note, so it stops short of a 5.

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

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

The description implies the tool's role as a read-only status check ('不会重试提交' tells the agent not to use it to re-submit), and the status caveats hint at when its results need follow-up. But it never names an alternative tool or states an explicit when-to-use condition relative to publish_note or cancel_prepared_note, so guidance remains inferred 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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely valuable context: returned content is untrusted web page data, which warns about prompt-injection risk. It also implies scroll-dependent retrieval behavior not captured by annotations.

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

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

Three tight sentences, front-loaded with the purpose before the caveats. Each sentence adds distinct value with no filler, though the untrusted-data warning could be positioned more logically relative to the keyword caveat.

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?

Covers the purpose, the keyword caveat, and the untrusted-data warning, which is solid given no output schema. But for a 6-parameter tool it omits meaningful explanation of platform, url (community page selection), scrolls, and limit, leaving the retrieval mechanics underspecified.

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

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

With 0% schema description coverage across 6 parameters, the description must carry the burden, but it only addresses the keyword parameter's semantics. It says nothing about url, platform, account, limit, or scrolls, leaving most parameters unexplained in both schema and description.

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

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

States a specific verb+resource (query notes) and clarifies scope: your own notes or a specified community page's notes. This distinguishes it from the singular get_note sibling, though it never names the alternative explicitly.

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

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

Adds a useful usage caveat that keyword only filters titles within the current scroll range rather than performing a full-site search, which tells the agent when this filter is and isn't appropriate. However, it gives no guidance on when to pick this tool over get_note or search_destinations.

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

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

Annotations declare the write-ish, open-world, non-idempotent profile, and the description adds real value beyond them: credentials stay on the local machine and cookies are never returned to the model. That privacy/side-effect disclosure is exactly the kind of context annotations cannot express, though nothing is said about what happens on repeated calls or about timeouts.

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 two clauses, front-loading what the tool does before the privacy constraint. No wasted text.

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 behavioral/privacy side is covered and the no-cookie statement partly substitutes for a missing output schema, but the two input parameters are undocumented in both schema and description, leaving the agent without guidance on how to invoke it.

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

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

Schema description coverage is 0% and the description says nothing about the 'platform' enum (ctrip/trip) or the 'account' selector. With two undocumented parameters, the description fails to compensate for the coverage 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?

States a specific verb and resource ('打开本地持久浏览器供用户登录'), making clear this launches a login flow rather than checking status. It is distinguishable from the check_login sibling, though it never names or contrasts with it 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?

The purpose implies the usage context (user needs to log in), but there is no explicit when-to-use, when-not-to-use, or pointer to the obvious alternative check_login for verifying an existing session.

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

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

Annotations already flag a non-read-only, non-idempotent, open-world write. The description adds value beyond that: it discloses the side effect (uploading assets to the platform), the boundary (does NOT submit the note), the authorization precondition, and the return shape (task ID + screenshot path) despite there being no output schema.

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

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

Two compact sentences, front-loaded with the action and its outputs, then the scope caveat and precondition. No redundant or filler content, though it could add a routing cue to publish_note 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?

For an 8-parameter mutation with no output schema, the description usefully covers the return values, the non-submission boundary, and the authorization prerequisite. However, it leaves the required fields undocumented, so an agent still lacks enough to populate the call confidently.

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 schema provides no field-level meaning. The description only alludes to 'local images' and a 'publish form', leaving required fields like platform, destination, destination_option, tags, and account entirely unexplained. It does not compensate for the coverage 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?

States a specific verb and resource: uploads user-specified local images and fills the publish form, returning a task ID and screenshot path. The clause '此步骤向平台上传素材但不提交笔记' explicitly distinguishes it from the sibling publish_note, so an agent can route between them without opening either 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?

Gives clear context: it prepares material without submitting, and states the precondition that user upload authorization is required. It does not explicitly say to call it before publish_note or name the alternatives, so guidance is contextual rather than fully prescriptive.

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

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

Annotations already declare write (readOnlyHint=false), open-world and idempotent behavior; the description adds real context beyond that: a user-confirmation gate, the consent semantics of accept_terms, and a no-retry rule. The no-retry advice sits in slight tension with idempotentHint=true, but it reads as operational caution (avoid acting on an ambiguous outcome) rather than a factual conflict with the annotation.

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 dense sentences, front-loaded with the action and then the gating conditions. Every sentence carries a distinct constraint (user confirmation, terms consent, no resubmit), with no filler. Slightly terse given the mutation risk, but not padded.

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 non-idempotent-looking publish step with no output schema, the description covers the preconditions and the ambiguous-result case, which is the main risk. However, it does not say what a successful submission returns or returns a job handle, and it omits the obvious resolution path (get_publish_status) that an agent needs when the result is unclear.

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 schema supplies names and types only. The description meaningfully explains accept_terms (explicit user consent to Trip.com material-ownership and platform terms), and '已预览的笔记' hints that job_id refers to a prepared note, but it never explains job_id's origin or what confirm actually gates. Partial compensation for a 3-parameter, 0%-coverage 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 verb+resource is specific: submit ('提交') a previously previewed note ('已预览的笔记'), which tells an agent this is the terminal publish step, not preparation. It does not name its closest siblings (prepare_note, get_publish_status), so the distinction must be inferred from the '已预览' wording. Clear, but sibling differentiation is left implicit.

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

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

Gives an explicit precondition (only after the user confirms the target account and specific content) plus two constraints: accept_terms requires explicit user consent to material ownership/platform terms, and no resubmission when the outcome is unclear. It stops short of naming get_publish_status as the way to resolve an unclear result, so the recovery path 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The '不会发布' (will not publish) clause largely restates that non-mutating trait, and the description adds the workflow context (label feeds prepare_note) but discloses nothing new about auth, rate limits, or result shape.

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 purpose front-loaded and no filler; the workflow link and the '不会发布' caveat are appended tightly. Appropriately sized for a simple 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?

With no output schema and 0% parameter coverage, the description partially compensates by hinting that returned labels feed prepare_note.destination_option. Still, it leaves the returned candidate structure and the meaning of account/platform unaddressed for a tool with two required parameters.

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

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

Schema description coverage is 0% and the description explains none of the three parameters (query, account, platform). It mentions '完整 label' but this refers to the returned value for destination_option, not to any input parameter, so the agent gets no added meaning for query length limits or the platform enum.

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 (query candidates) and resource (destination/location candidates within the publish form), which an agent can distinguish from list_notes or get_note. It also clarifies the downstream consumer (prepare_note.destination_option), grounding the purpose in the publishing workflow, though it doesn't explicitly contrast with other sibling tools.

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

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

Usage is implied: this is a pre-step for the publish flow whose output feeds prepare_note.destination_option, and the note '不会发布' signals it is not a publishing action. However, there is no explicit when-to-use statement or naming of alternatives among the nine siblings.

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