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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false. The description adds that it returns statistical definitions, sources and date basis, and when to consult it, but does not detail return format or auth/rate limits. With annotations covering safety, 3.

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 short sentence front-loads the verb and content; every clause adds value with no repetition. 5.

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 covers purpose, return content and usage timing, and annotations cover safety. However, with no output schema and zero parameter descriptions, the unexplained release_id is a notable gap. 3.

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 mentions neither report_id nor release_id. Only the word '报告' weakly implies report_id; release_id is entirely unexplained, so 2.

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') and resource ('报告统计口径、原始来源和日期依据'), making clear it returns metadata rather than report content. It does not explicitly name sibling alternatives, so 4.

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 instructs to check here before analysis or cross-report comparison, giving clear usage context. It lacks exclusions or named alternative tools, so 4.

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 openWorld, so the safety profile is covered. The description adds real value with the 20-records-per-page pagination fact and the aggregation exclusion, but says nothing about ordering, total counts, or what a page beyond the last returns.

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 resource and scope front-loaded and the pagination constraint appended; every clause carries information. Slight awkwardness in packing the exclusion and the page size into the same run-on line.

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?

Five parameters with zero schema descriptions, no output schema, and no annotation gaps to hide behind — the description should at minimum explain the id filters and pagination edge behavior. It covers the page size only, leaving an agent unable to use faction_id, opponent_id or release_id 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%, so the description carries the full burden and largely fails: page, faction_id, opponent_id and release_id are never mentioned or explained. Worse, '按所选报告的日期、规则、地区和赛制查询' suggests filtering comes from the report, which obscures the fact that the caller can narrow results with three separate id filters.

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 ('查询已存对阵') scoped to a selected report, and explicitly contrasts itself with a cross-period MFM aggregation. Siblings (list_reports, get_roster, get_data_notes) are unrelated resources, so no naming is needed, but the object '对阵' is never defined in domain terms.

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 clause '不是跨期MFM汇总' rules out one adjacent use case, and the mention of report-scoped date/rules/region/format implies the report_id prerequisite. There is no positive guidance on when to pick this over re-querying the report itself, and no alternative tool is named.

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, open-world behavior, so the safety profile does not need to be repeated. The definition adds useful content about the data shape: faction statistics are precomputed, and raw and estimated win rates are kept separately. It says nothing about pagination, size, or failure behavior, so it is helpful but not rich.

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?

It is a single dense sentence with no filler, and the main purpose is front-loaded before the release_id usage note. It is efficient, though a semicolon-separated clause makes it slightly packed.

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 definition partially compensates by naming the returned win-rate fields. For a 3-parameter read tool with 0% schema coverage, however, the meaning of report_id versus faction_id and the default null behavior are only inferred, leaving 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 0%, so the schema provides no descriptions for report_id, faction_id, or release_id. The definition explains release_id's role (version pinning) and implies faction_id via 阵营统计, which partly compensates. report_id's 64-hex format and faction_id's nullability remain undocumented in prose.

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 definition gives a specific verb and resource (读取报告和阵营统计), and adds the key distinction that precomputed faction statistics are returned alongside the report. It also states what is retained in the data (raw vs estimated win rates). It does not explicitly name which sibling to use instead, but the term 指定 (specified) shows it is not a listing tool like list_reports.

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 definition implies the tool needs a known report id and adds one concrete usage rule: use release_id to pin the version. However, it never says when to choose this instead of list_reports or get_matchups, and it gives no exclusions or prerequisites.

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 and non-destructive, so the safety bar is low. The description still adds real behavioral content absent from the annotations: the returned data must preserve original text, Chinese translation, source, and unconfirmed status, and must not zero-fill unknown values — a fidelity guarantee an agent could not infer otherwise.

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 the verb first and no filler; each clause (source fidelity, translation, unconfirmed status, no zero-filling) carries distinct information. It is dense 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?

With no output schema, the description usefully sketches the shape of the returned roster (original text, translation, source, unconfirmed flags) and the null-vs-zero convention. However, it leaves the required case_id and the optional release_id unexplained, which is a material gap for a fetch keyed on three identifiers.

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 three parameters, so the description must compensate. It only gestures at report_id ('该报告关联的') and says nothing about case_id (a required 64-hex identifier) or the optional release_id / its null default, leaving the two most opaque required parameters entirely 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 (读取/read) and resource (一份公开军表 – one public roster) and scopes it to the report in context, which distinguishes it from the plural sibling list_rosters and from get_report. It does not explicitly contrast with those siblings, 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?

Usage is only implied: '该报告关联的' signals that this is the report-scoped single-roster fetch versus the list-level tool. There is no explicit when-to-use, when-not-to-use, or named alternative, and the role of the optional release_id in choosing which roster is never addressed.

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 the safety profile (read-only, idempotent, non-destructive, open-world). The description adds meaningful behavior beyond annotations: 20 results per page and date filtering based on the report's statistical window.

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-loads the core purpose before date, pagination, and workflow details. Every clause carries some useful information, though the extreme brevity leaves gaps rather than 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?

For a list tool with 8 optional filters, no output schema, and no schema parameter descriptions, the description is too thin. It gives page size and mentions report_id/release_id in results, but does not explain most filter behavior or return shape.

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 description must compensate but largely does not. It only clarifies date-window filtering and page size, leaving type, format, report_source, version_id, and release_id filter semantics 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 gives a clear verb and resource: find published/live reports. It adds scope with the date-window qualification, but it does not explicitly distinguish this list operation from the sibling get_report.

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 line about first obtaining report_id and release_id from the results implies a useful workflow entry point for later detail calls. However, it does not explicitly state when to use this instead of get_report or other siblings, nor does it state any exclusions.

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 already declare readOnlyHint, idempotentHint, non-destructive, and openWorld, so the description does not need to cover safety. It usefully adds the fixed page size of 20 items per page and the case_id continuation path to get_roster, but it says nothing about the maximum page cap, what an empty result means, or how summaries differ from full rosters.

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 compact sentence with two clauses, front-loading the resource and scope, then the workflow step. Every element earns its place and nothing is 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?

With no output schema, the description does convey the return shape (summary rows with case_id, paginated by 20) and the workflow continuation, which covers a lot. However, for a four-parameter filtered list tool, the unexplained faction_id and release_id filters, plus no guidance on paging past the first page, leave the definition incomplete.

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 carry the meaning of the four parameters, yet it explains only report_id (implicitly, as 该报告) and the page size. The faction_id and release_id filters, which determine what gets listed, are never mentioned, so the agent cannot infer what those parameters do from either source.

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: 列出该报告的军表摘要 (list roster summaries for this report), and it also says that get_roster is the companion call for details, so the agent can distinguish this summary listing from the detail fetch. It does not clarify the relationship to list_reports or the other sibling tools, so it falls 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?

It specifies the context in which to use the tool: to browse public rosters attached to a given report, and it prescribes the follow-up step of reading case_id from the results and then calling get_roster. It gives no explicit exclusions about when NOT to use it, and it does not say when faction_id or release_id filtering is appropriate.

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