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

Beyond the readOnlyHint and idempotentHint annotations, the description adds meaningful privacy behavior (does not read or return passwords or cookies) and explains the visible-window behavior when open_login_window is true. This provides context not captured by annotations 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?

The description is two sentences, front-loaded with the core purpose, and includes only essential details (privacy guarantee and parameter behavior). No redundant or filler content.

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 read-only tool with one parameter and an output schema, the description covers purpose, parameter semantics, and safe behavior. It lacks explicit sibling differentiation, but the tool's simplicity and existing output schema keep the description reasonably 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?

Though the schema has no parameter description (0% coverage), the description explains that setting open_login_window=true keeps a visible window for login or CAPTCHA, implying the default false behavior. This adds semantic value to an otherwise bare boolean parameter.

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

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

The description clearly states the tool checks login status for WOS, IEEE, and Tencent Docs in a persistent Chrome instance, using a specific verb and resource scope. It also explicitly distinguishes itself from search/download siblings by focusing on session verification rather than content retrieval.

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 usage for verifying sessions before search or download, and explains the open_login_window parameter for interactive login/CAPTCHA. However, it does not explicitly say when to use this tool over alternatives (e.g., 'use before search_wos') or provide exclusion criteria.

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?

The description discloses 'recoverable' behavior, the absence of online retrieval, and a worksheet prohibition. However, with all annotations false, the description carries full burden, and it lacks details on side effects, state persistence, or interaction with other system components like browser sessions.

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 two sentences, direct, and without fluff. It front-loads the primary purpose and adds a key constraint, achieving high information density in minimal 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?

This is a complex 8-parameter tool with no schema descriptions and no annotations. The description covers only the high-level purpose and one parameter constraint, leaving major gaps in parameter understanding and usage context. It is far from adequate for an agent 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 has 0% description coverage, and the description only addresses target_sheet (prohibiting 'Sheet1'). It does not explain topics, years, institution, pdf_directory, tencent_doc_url, or accept_preprints. The WOS query mention implies some parameters are search criteria, but explicit semantics are missing.

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 the tool creates a recoverable local run record and generates a WOS advanced search query, and explicitly notes it does not perform online retrieval. This specific verb+resource description distinguishes it from sibling search_wos, which likely executes the actual search.

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 phrase '不执行联网检索' (does not perform online retrieval) implies use for preparation rather than actual searching, but no explicit when/when-not conditions or alternative tools are named. The target worksheet restriction is a constraint, not 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?

The description goes well beyond the annotations by disclosing the download source order, HTTPS-only requirement, file validation steps (PDF header, size, SHA-256), and the explicit boundary of not bypassing login/captcha/paywalls. These details align with the annotations (non-destructive, idempotent) and add significant behavioral context.

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

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

The description is a single, dense sentence that efficiently packs the action, source priority, validation rules, and ethical constraints without redundant words. It is front-loaded with the verb and resource, making it easy to parse.

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 description thoroughly covers the tool's behavioral specifics, and the output schema presumably handles return values. However, it omits any explanation of the input parameter and the prerequisite context (e.g., needing a completed run), which leaves a minor gap for practical use.

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 only one parameter, run_id, with 0% schema description coverage, and the tool description does not mention it at all. The agent gets no explanation of what run_id represents or how to obtain it, so the description fails to compensate for the missing schema documentation.

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 specifies the tool's function: downloading fulltext PDFs with a defined priority order (IEEE official, publisher open, preprint/author manuscript) and validation criteria. This specific verb+resource statement distinguishes it from sibling tools like search_wos or sync_results, making the purpose immediately clear.

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 is for downloading fulltexts after a search run, but it does not explicitly state when to use it or mention alternatives. There is no when-not guidance or exclusion, leaving usage context mostly implied rather than explicit.

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

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

Annotations already assert readOnlyHint, idempotentHint, and destructiveHint, and the description adds non-obvious behavioral details: it does not start a browser and does not modify files, and it reads both local run state and Tencent doc/PDF paths. This goes beyond the structured annotations, though it does not discuss error behavior or return format (which is covered by an output schema).

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

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

The description is a single, front-loaded sentence that starts with the action and lists the exact data returned, followed by a decisive side-effect disclaimer. Every element earns its place, and there is no redundant phrasing.

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 one simple parameter, an output schema present, and annotations covering safety, the description fully explains what the tool does, what data it reads, and what side effects it avoids. This is complete for the tool's low complexity and leaves no major gap for an agent.

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 input schema only defines run_id as a string with no description, and schema_description_coverage is 0%. The description compensates by clarifying that the run_id is a local identifier and enumerating what will be read from it, which gives the agent enough context to understand the parameter's role without over-specifying format.

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

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

The description uses the specific verb '读取' (read) and identifies the resource as the local run_id's status fields (stage, pending user action, errors, Tencent doc target, PDF directory). It also explicitly states '不启动浏览器或修改文件' (does not start browser or modify files), which differentiates it from sibling tools like check_browser_session and sync_results.

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 clearly indicates this is a read-only status check for a local run_id, and the negative clause about not starting the browser provides a relevant exclusion. However, it does not explicitly name alternative tools or state when to prefer this over check_browser_session or sync_results, 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?

Beyond the annotations (readOnlyHint=false, idempotentHint=true), the description adds key behavioral details: it reads from a Tencent doc, merges local overrides, writes to a .runtime file, and does not modify the source. This provides transparency about side effects and the 'read-only' nuance, which is valuable. No contradiction with 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?

The description is a single sentence that front-loads the core action and includes the most important caveat (no modification of source). Every word earns its place with no redundant 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 tool with 2 parameters and an output schema, the description adequately covers inputs, process, and side effects. It doesn't explain the output schema (which exists), so that is not required. The only gap is the lack of explicit parameter mapping, but overall it is complete enough for selection and invocation.

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

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

With schema description coverage at 0%, the description must compensate. It mentions the 'specified Tencent doc source worksheet', which hints at source_sheet and tencent_doc_url, but does not explicitly map parameter names or explain format. It adds some meaning but not enough to fully compensate for the 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 clearly states the tool's function: reads journal names and CAS partitions from a specified Tencent doc worksheet, merges local overrides, and writes to a .runtime mapping. It also explicitly notes it does not modify the source worksheet, distinguishing it from sibling tools like sync_results.

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 clear context about its purpose and side effects (no modification to source sheet), implying when it should be used. However, it does not explicitly mention alternatives or when not to use it, so it falls 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?

The description discloses the stop condition at 500 hits and the filtering behavior (by year, unit, SCI-EXPANDED), which adds context beyond annotations. It also mentions exporting complete records, aligning with readOnlyHint=false. However, it does not specify the export destination or whether run status is updated, leaving some behavioral gaps.

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

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

The description is a single dense sentence that efficiently packs the tool's purpose, execution details, filtering, and stop condition without fluff. Every clause contributes essential information, and it is well front-loaded.

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 moderately complex, and while the output schema exists, the description misses parameter semantics and does not clarify prerequisites (e.g., creating a run first) or edge cases. It covers the main behavior but leaves gaps for an agent to decide when and how 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?

The input schema has a single required parameter run_id with no description, and the description does not explain what run_id refers to or how it relates to the search run. Schema coverage is 0%, and the description fails to compensate, providing only implicit meaning through the word '运行中的'.

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 the tool executes an advanced search in WOS Core Collection using a dedicated Chrome, exports complete records, and filters them by year, unit, and SCI-EXPANDED. The phrase '运行中的' (ongoing) distinguishes it from creating a search run, making it distinct from sibling tools like create_search_run. It includes specific action, resource, and constraints.

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 context such as the need for a dedicated Chrome and the stop condition at 500 hits, but it does not explicitly state when to use this tool versus alternatives like create_search_run or get_run_status. It implies usage for an existing run via '运行中的', but no exclusions or alternative recommendations are given.

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

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

Beyond the annotations (destructiveHint, readOnlyHint, etc.), the description reveals specific side effects: it updates [MCP] remarks, preserves non-MCP manual J-column remarks and existing attachments, uploads PDFs, and sorts rows. These details give the agent a clear picture of the tool's non-obvious behaviors, exceeding the annotation baseline.

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 two sentences long, front-loaded with the primary actions (write, upload, sort), and each sentence adds unique value—the second sentence clarifies what is preserved. No wasted words or repetition of schema details.

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 complex sync tool with multiple operations and side effects, the description covers all key aspects: the data written, the upload of PDFs, sorting, and the selective update of remarks. The existence of an output schema means return values need no explanation, so the description is sufficiently complete for an agent to invoke the tool accurately.

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 zero description coverage, and the description only indirectly references run_id via '运行指定' (specified by the run). This gives some meaning to the parameter but does not explain its format, constraints, or how it maps to the worksheet. Since there is only one parameter, it is adequate but not rich.

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 specific verbs ('incrementally write', 'upload', 'sort') and identifies the resource (Tencent Docs worksheet), clearly distinguishing it from sibling tools like search_wos and download_fulltext. It also mentions the specific columns (A-J) and remark handling, leaving no ambiguity about its function.

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 usage when you need to sync results from a run to Tencent Docs, and specifies that it will not overwrite manual remarks or existing attachments, which is a caution. However, it does not explicitly state when not to use it or name alternative tools, so it falls 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.