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

Annotations already declare readOnly, idempotent and non-destructive, so the safety profile is covered. The description adds genuinely new behavior: empty keyword returns everything and paging is driven by next_offset. It does not say whether next_offset comes from the response or how many results a page yields.

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 lookup purpose front-loaded and the empty-keyword and paging rules appended. No filler, though the semicolon-dense packing makes the paging clause slightly easy to miss.

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?

Three optional parameters and no output schema; the description covers the lookup intent and one paging cursor but does not describe what a board record contains or confirm that next_offset is returned. Adequate, but a small gap remains for an agent trying to page correctly.

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

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

Schema description coverage is 0%, so the description must compensate. It explains keyword (empty = list all) and offset-based paging via next_offset, but leaves limit (default 30, max 50) completely undocumented.

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 (查找) and resource (版面), plus the concrete output (版面 ID) and its downstream purpose (供版内搜索使用). This clearly separates it from the read/search siblings, though it never names them 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?

Gives one useful usage rule — an empty keyword lists all boards — and implies it should be called before board-scoped searching. There is no explicit guidance on when to prefer this over cc98_search or how it relates to the other search tools.

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/openWorld/destructive=false, so safety is covered. The description adds real behavioral context: pagination via next, offset semantics, and raw-vs-rendered output. It still says nothing about default page size, limits, or return 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?

Three compact sentences, front-loaded with what is read and why; the link/offset nuance and continuation cue follow logically. Slightly dense packing of offset semantics, but 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?

There is no output schema and the description mentions a next field without explaining the return payload; it also leaves three of six input parameters unexplained. Adequate for a read tool but not complete given the 0% schema coverage.

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

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

Schema description coverage is 0%, so the description must compensate, and it explains only 3 of 6 parameters (topic accepts ID or link, from is a 0-based floor offset defaulting to the link position, format raw). size, content_offset, and max_characters remain completely undocumented in both schema and description, which matters for pagination.

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 (读取主题和指定楼层) and adds a disambiguating purpose (核对搜索证据) that separates it from the sibling search tools. It does not name sibling tools explicitly, but the intent 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?

Frames the tool as a follow-up to searching (用于核对搜索证据) and explains continuation via next, which is clear usage context. There is no explicit when-not-to-use or a direct pointer to cc98_search vs cc98_search_results.

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), so the bar is lower, and the description still adds real behavioral context: results are deduped/reranked, snippets come from verified first posts, and coverage is reported as a snapshot rather than an exhaustive index. That tells the agent results are ranked and potentially partial. It does not explain what 'refresh' does or what a 'coverage range' looks like, which keeps 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?

Four short, dense clauses with no filler. The ordering is mildly counterproductive — retrieval-pipeline mechanics lead before the plain statement of what the tool is — but nothing is wasted.

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 taking 9 parameters with no output schema and no schema descriptions, this description is well short of what an agent needs: the two main tuning enums are undocumented and the shape of the returned 'snapshot' is only gestured at. An agent could fire a bare keyword call, but could not confidently use most of the optional 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?

With 9 parameters and 0% schema description coverage, the description must carry parameter meaning, and it explains only one ('terms' corrects Chinese segmentation). The trade-off behind depth's quick/balanced/deep enum is unexplained, as are sort, limit, refresh, board_id, and the created_after/created_before date bounds. That leaves most of the calling surface undocumented.

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 does state what the tool is: a keyword search over CC98 that does multi-path recall, dedup/rerank, first-post verification, and returns hit snippets plus a coverage snapshot. The closing clause 'not full-site full-text search' usefully bounds the scope. It loses a point because the core verb (search) is buried in pipeline jargon, and differentiation from the sibling cc98_search_results is left implicit rather than stated.

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

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

'terms 可纠正中文分词' gives one concrete trigger for using a parameter, and '不是全站全文检索' signals an expectation-setting boundary. But there is no guidance on when to prefer this over cc98_search_results, no mention of how to page through the returned snapshot, and no mention of what depth/sort/refresh are for when choosing the call.

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, and the description adds genuinely useful behavior beyond them: the snapshot has a 15-minute TTL and dies on service restart or account switch. It stops short of saying what happens when the search_id is expired (empty list vs. error) and describes paging in terms of 'next_offset' that does not exist 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?

Two short sentences, front-loaded with what is being read and the key constraint that no new search occurs. No filler, and the TTL caveat is placed where an agent will see it before calling.

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 read-only, idempotent continuation tool with no output schema, the description covers the essentials: source identity, no re-search, and the lifetime of the snapshot. It is still thin on return shape (what a 'candidate' looks like, total counts) and on limit behavior, but those are secondary for a pager.

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

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

Schema coverage is 0%, so the description must carry the parameter burden, but it covers only search_id's role and a continuation concept. It never mentions limit or its default of 10 / maximum of 20, and it calls the paging parameter 'next_offset' while the schema parameter is 'offset', which risks mis-invocation.

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 (读取/续读) and resource (已有候选/search results snapshot), and explicitly disclaims searching again, which separates it from the sibling cc98_search. An agent can tell it apart from cc98_search and cc98_read_topic without opening any schema.

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

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

It clearly says this reads an existing search by search_id rather than performing a new search, and adds a 15-minute validity window plus invalidation on restart or account switch, which is real usage context. However it never explicitly names the prerequisite tool (cc98_search) that produces search_id, so the routing direction 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 establish readOnly/idempotent/non-destructive and openWorldHint, and the description adds the key detail: the default mode stays local, while check=true actually hits the network to read the current account. That clarifies the network-cost difference between modes, though it doesn't say what is reported on failure.

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 primary behavior front-loaded and the flag semantics appended after the semicolon. Nothing is wasted.

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 diagnostic/status tool with no output schema, the description never hints at what is returned (login state, username, connection result, error shape). Safety is covered by annotations, but an agent can't anticipate the result payload from the text alone.

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

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

Schema coverage is 0% (the check boolean has no description), so the description must carry the meaning. It explains exactly what true triggers — reading the current account to verify direct connection and login — which makes the parameter actionable; the false case is only implied by '检查本地登录配置'.

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 action (检查本地登录配置) plus a second mode (读取当前账号以验证直连). This clearly distinguishes it from siblings like cc98_read_topic and cc98_search, which fetch content, though it never names them 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 conditional 'check=true 时' implies when to use each mode, but the description never states when to call this tool at all (e.g. before other cc98 tools, or after auth failures) nor any exclusions. Usage is inferable rather than stated.

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