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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld), so the description's added context is what earns credit: the 20-record cap per call, the exact return fields, and the explicit statement that question bodies are not read. It does not mention error behavior or what happens with invalid/nonexistent IDs.

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: the read action plus return fields come first, then the distinguishing purpose, then the negative scope. No filler, and everything needed to route the call is 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?

With no output schema, the description correctly names the returned fields, and with annotations covering safety it need not re-explain read-only behavior. It does not address behavior when some of the up-to-20 IDs are missing or invalid, which is a minor gap for a batch lookup tool.

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%, but the description compensates by stating the 20-item ceiling (matching maxItems) and, more importantly, indicating that the record_ids originate from a prior search rather than being arbitrary identifiers. The numeric-string pattern is left to the schema, but the origin constraint is real added meaning.

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 (读取检索得到的试卷详情) and enumerates the returned fields: 学年、学期、考试类型. It also explicitly contrasts with the content-fetching sibling by noting 不读取题目正文, so an agent can separate it from paperbridge_download without opening schemas.

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 a clear usage context (用于区分同年同名的试卷) and implies a workflow prerequisite by scoping input to 检索得到的 records, i.e. IDs must come from paperbridge_search. It does not explicitly name or exclude the download sibling as an alternative, 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?

Adds real behavior beyond the annotations: files are written locally (consistent with readOnlyHint=false), downloads happen in order, each PDF is verified, and the response deliberately excludes cookies, tokens, and signed URLs. The remaining gap is what a failed/partial verification looks like and whether re-downloads are skipped, but the disclosure is well above 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?

Purpose is front-loaded in the first clause; every following clause (provenance, cap, ordering, verification, credential non-return) adds information. It is dense and bundles several concerns into one long sentence, but there is no 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?

For a single-parameter tool with no output schema, the description covers source of IDs, batch limit, ordering, verification, and output content restrictions — everything needed to invoke it correctly and interpret 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?

Only one parameter with 0% schema description coverage, so the description carries the burden — it supplies the provenance constraint (must come from paperbridge_search) and restates the 20-item cap. It does not explain the numeric-string pattern, but the schema already enforces 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?

States a concrete verb+resource: download selected exam-paper PDFs from search results and archive them locally by course code. The scope ('from search results', 'to your own computer') clearly separates it from paperbridge_search and paperbridge_details.

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 routes the agent: record_ids must originate from paperbridge_search, and at most 20 per call. It gives a clear precondition and a batch limit, though it does not state any when-not-to-use case (e.g. already-downloaded items) or name an alternative tool for bulk retrieval.

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 annotations declare readOnlyHint=false, openWorldHint=true, and destructiveHint=false, but the description adds critical behavior the annotations do not cover: it returns immediately, does not fill in passwords on the user's behalf, and does not auto-agree to the usage agreement. This human-in-the-loop, non-blocking behavior is essential for correct invocation.

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, starting with the tool's core action and then covering the required human steps, immediate return, follow-up tool, and constraints. Every clause earns its place with no redundant restatement of the name or 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?

Given the tool's simplicity (no parameters, no output schema) and the annotation coverage for openness and non-destructiveness, the description is complete. It tells the agent exactly what will happen, what the user must do, and what to do next, leaving no critical gap for correct 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?

The tool has zero parameters, so there are no parameter semantics to clarify. Per the evaluation baseline for 0-parameter tools, a score of 4 is appropriate.

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

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

The description states a specific verb and resource: '打开试卷库专用登录窗口' (open the dedicated login window for the exam paper library). It also distinguishes the tool from siblings by naming paperbridge_status as the follow-up checker, so an agent can tell this apart from search, download, or details without opening another 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?

The description gives clear usage context: the user completes SSO, reads and confirms the agreement, searches a course code, and then the agent should check with paperbridge_status. It lacks an explicit when-not-to-use condition (e.g., if already authenticated), so it is clear but not fully exhaustive.

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/openWorld/non-destructive, so the safety profile is covered; the description adds real value beyond that by disclosing the auth prerequisite (login first), the access-limited result scope, and the pagination contract via next_page. It does not discuss rate limits or result caps, which is a minor gap rather than a contradiction.

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?

Four short, front-loaded clauses, each carrying a distinct instruction (scope, fields, paging, selection, auth) with no filler. The terse telegraphic style is efficient, though the ordering of the login prerequisite last slightly buries an action the agent must take before anything else.

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 correctly compensates by listing the returned fields, and it covers scope, pagination, downstream selection, and auth. The only real omission is the meaning of the page/page_size inputs, so an agent can call it correctly but must infer paging granularity.

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 has to carry parameter meaning. It clarifies course_code's purpose and hints at paging behavior through next_page, but page and page_size (with their 1-100 bounds) are never explained, so the compensation is only partial.

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 (retrieve past exam papers by course code) plus scope (only ones the caller has access to) and even names the return fields (title, academic year, record_id). It explicitly distinguishes itself from paperbridge_details by defining the selection step as details' job, so an agent can tell the siblings apart without opening schemas.

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 operational rules: continue paging when next_page is present, do not guess paper IDs, call paperbridge_details before choosing by 正考/补考 or semester rather than trusting a same-named title, and call paperbridge_login first when unauthenticated. Both when-to-use and when-to-defer are covered with named alternatives.

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=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description's added value is the note that PaperBridge uses an independent per-user session, which tells the agent the status is caller-specific rather than global. It says nothing about polling cadence, whether concurrent login attempts matter, or what the returned progress represents — meaningful gaps for a tool whose whole purpose is watching login progress.

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, no filler, with the resource and the session caveat front-loaded. Every clause carries information an agent needs.

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 no parameters, the description is the only source of detail about what the agent will get back. It identifies the subject (login status and progress) but never describes what those fields look like or their possible states, leaving the agent to guess on the return value. Adequate but with a clear 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?

The tool takes zero parameters, so the schema carries no semantic burden and 4 is the baseline. The description correctly implies all state is resolved from the caller's session rather than from arguments.

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 (检查) plus resource (登录状态和登录进度) scoped to 西浦图书馆历年试卷库, so the agent knows this is a status read rather than a login action. It does not name or contrast with the sibling paperbridge_login, which is the tool it is most easily confused with, 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 explicit when-to-use, when-not-to-use, or alternative routing. The word 进度 implies polling during login, but the description never says to call this while paperbridge_login runs, nor what to do with the result. Usage is only faintly inferable from the purpose statement.

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