China Industry Intel

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds substantive context beyond them: the specific fields returned, the explicit set of fields NOT returned, and Chinese-alias support. It stops short of noting that results are bounded by the limit parameter ('small selection' only gestures at it).

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 short sentences, each carrying information, with the primary capability front-loaded before the exclusion list. Slightly vague wording ('small selection') is the only soft spot; there is no filler or repetition.

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 lookup with no output schema, the description does the important work of describing what is returned and what is not. The remaining gap is parameter-level detail (limit behavior, query format beyond alias support), which leaves the definition adequate but not fully self-contained.

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 both parameters, so the description must compensate, and it largely does not. 'Chinese aliases supported' usefully clarifies that the query string accepts Chinese aliases, but the limit parameter (default 5, max 10) is never explained and 'query' semantics remain unspecified.

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 ('Find ... company names, CII profile links and official identity URLs') and enumerates the returned artifacts, so the agent knows exactly what this lookup yields. It does not explicitly differentiate itself from the article-oriented siblings, but the domain (company identity) is distinct enough to disambiguate.

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?

'Does not provide financials, customers, headquarters or verified fact sheets' sets negative scope that helps an agent decide when this tool is insufficient, and 'Chinese aliases supported' hints at query use. However, no alternative tool is named for the excluded data needs, so routing guidance is only implied.

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, closed-world behavior, and the description adds useful negatives: no full body, no private records, no arbitrary URL fetching, and absent IDs are out of snapshot. It does not discuss rate limits or response shape, but the annotations carry the safety profile well.

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 carries purpose, scope, and exclusion constraints with 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?

Given a simple one-param read-only tool with full annotation coverage and no output schema, the description supplies what the schema lacks about scope and exclusions. The only minor gap is return value shape, though that is partly implied by 'excerpt and disclosed sources'.

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 only one parameter and 0% schema description coverage, the description says 'one selected article ID' and that absent IDs are not in the snapshot, but it adds no format, type, or validation details beyond the implicit integer in the schema. Baseline 3 for a simple single required param 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?

States a specific verb and resource ('Get the public publisher excerpt and disclosed sources of one selected article ID') and clearly bounds scope against siblings like search_articles by emphasizing a single selected ID and the absence of URL fetching.

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?

Clarifies that this is for one selected article ID and that absent IDs are not in the snapshot, implying use after selection via search_articles. It does not explicitly name search_articles as the alternative, so it stops just 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?

Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive), and the description adds genuinely new traits: matching is literal rather than semantic, the corpus is a static dated snapshot, and results carry publisher attribution with canonical and source links. Good value beyond the structured fields.

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, zero filler, with the scope statement and its exclusion front-loaded before the return-shape sentence. 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?

With no output schema the description usefully sketches the return payload (excerpts, URLs, source links), and it defines the corpus boundary for a 5-parameter tool. Remaining gaps are the undocumented limit parameter and date-format expectations, which are minor but non-trivial.

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 parameter meaning. It maps query to 'literal keywords', names the industry filter, and clarifies the date bounds are inclusive and UTC — real added meaning. But limit is never mentioned, and date format/enum values are left entirely to the 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?

Specific verb (search) plus a clearly bounded resource (a small dated CII metadata snapshot) and the searchable dimensions (literal keywords, industry, inclusive UTC dates). The negative scoping ("not whole-site or live search") sharpens what it is, though it does not name or contrast the siblings find_company / get_article_summary.

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?

States the context of use (literal keyword lookup inside a static dated snapshot) and, more usefully, an explicit exclusion: it is not whole-site or live search. No alternative tool is named for those excluded cases, so an agent must still infer where to go for live or non-snapshot queries.

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