ReportGem Global Research

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

Beyond the annotations it discloses real behavioral traits: results are bounded and page-cited, sequential reads are resumable via next_cursor, and unmatched material is never surfaced as verified evidence — a meaningful quality guardrail. Note the annotations declare readOnlyHint=false for what the description frames as a pure retrieval operation; this is an inconsistency worth confirming, though it may reflect server-side cursor state rather than a write.

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?

Front-loaded and free of filler, with the two modes stated up front. However, the Chinese sentence is a full duplicate of the English one, roughly doubling the description's length without adding information, so not every sentence earns its place.

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 an output schema present, return-shape explanation is not required, and the description covers both modes plus the no-false-evidence guardrail for a 7-parameter tool. The remaining gap is the absence of any relationship to the search_* siblings that supply source_type and source_id.

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 100%, so every parameter (query, cursor, start_page, max_passages, reading_mode, source_id, source_type) is already documented in the schema. The description adds only the tool-level link between sequential mode and next_cursor, which the schema already states, so the baseline 3 applies.

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: 'Return bounded, page-cited source excerpts, or a sequential reading window... for whole documents', and names the two operating modes. It never mentions the sibling search tools, so an agent relies on the schema line 'Source identifier returned by a search tool' to infer the retrieve-after-search pairing.

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 implicitly distinguishes the two modes ('reading_mode="sequential" with next_cursor' for whole documents vs. excerpts for a claim), which is useful mode-selection guidance. It gives no explicit rule for when to call this instead of search_filings/search_meetings/search_research, and no guidance on behavior when the query yields no match beyond the guardrail sentence.

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 openWorldHint=false, destructiveHint=false, and no output schema dependency, so the description only needs to add color. It contributes that results include verifiable internal source links, but says nothing about result ordering, freshness, coverage of markets, or rate limits. Note that readOnlyHint=false is slightly surprising for a search verb, and the description neither explains nor contradicts this.

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, front-loaded sentences with no wasted framing; the bilingual restatement is a deliberate accessibility choice rather than padding. The one thing missing is structure — the scope, return-content, and market details are packed into a single sentence rather than separated.

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 six fully documented parameters and an output schema, the definition covers what the tool searches and what it returns, which is most of what an agent needs. Remaining gaps — result ordering and whether limits truncate silently — are modest for a read-style search 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 100% and all six parameters carry their own descriptions, including the market enum and ISO date formats. The description adds no additional meaning beyond what the schema already documents, so the baseline 3 applies.

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 names a specific verb+resource: searching US SEC filings and China listed-company announcements, plus a notion of what comes back (internal source links). The resource noun alone separates it from siblings like search_meetings, search_research, and search_visuals, though no sibling is ever named 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?

Usage is only implied by the resource: an agent can infer 'use this when you need SEC filings or China announcements.' There is no statement of when to prefer get_evidence or search_research instead, and no prerequisites (query length, market defaults) are discussed.

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 non-read-only, non-idempotent, and non-destructive behavior, and the description adds useful result semantics by noting that body-text evidence is distinguished from listing-only hits. However, it does not clarify the surprising non-read-only side effect or explain permissions, rate limits, or other operational behavior.

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 compact sentences with the purpose and result-classification front-loaded. The bilingual repetition is acceptable but adds some length without new 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 six-parameter search tool with an output schema, the description covers the corpus and one important result distinction but omits filter scope, selection guidance, and side-effect context. The output schema reduces the need to explain return shape, but routing guidance remains thin.

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 100%, so the input schema already documents query, region, date filters, limit, and output language. The description adds no parameter-level meaning beyond what the schema provides, so the baseline of 3 applies.

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 the specific verb 'Search' and the resource 'global and China earnings-call transcripts and meeting notes,' plus a result distinction between body-text evidence and listing-only hits. The domain is clear, though it does not explicitly differentiate itself from sibling tools such as search_filings or search_research.

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?

Provides no explicit when-to-use or when-not-to-use guidance relative to search_filings, search_research, search_visuals, or get_evidence. Usage is only implied by the meeting/transcript resource, leaving the agent to infer routing.

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 adds genuine behavioral context beyond the annotations: results are bounded metadata and real excerpts are returned only when the indexed body matches, so absence of excerpts is expected rather than an error. However, the annotations declare readOnlyHint=false for what is described as a pure search/retrieval operation, and the description does not clarify this discrepancy or explain any side effects, auth needs, or rate limits.

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?

Front-loaded with the verb and resource, then the return behavior; two compact sentences with no filler. The Chinese sentence is a near-exact restatement for a bilingual audience, which doubles the length without adding new 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 an output schema present, the description need not detail return values, and it still flags the excerpt-when-indexed caveat, which is the main behavioral surprise. For a five-parameter read-style search tool with full schema coverage and sibling tools, the description is nearly sufficient; only guidance on choosing this versus get_evidence/search_filings is missing.

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 100%, so all five parameters (query, limit, date_from, date_to, sources) are already documented in the schema, including the source-group meanings. The description's facet list lightly reinforces what query accepts, but adds no format, tokenization, or matching semantics beyond 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?

States a specific verb (Search) and a concrete resource set (sell-side research reports and academic papers) plus the facets it searches over (company, ticker, broker, industry, theme, date). That resource is clearly distinguishable from search_filings, search_meetings and search_visuals, but the description never names those siblings or draws the boundary 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?

Usage is only implied: an agent can infer this is the tool for broker/academic research text, and the sources field guidance ('Pass only the groups you need') nudges source narrowing. There is no explicit when-to-use vs when-to-use-get_evidence or search_filings guidance, and no stated prerequisites or 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?

Annotations already cover the safety profile (destructiveHint=false, openWorldHint=false), and the word 'indexed' is consistent with a closed corpus. The description adds the useful fact that results carry report and page provenance, but says nothing about ranking, pagination, or why readOnlyHint is false for what appears to be a pure query — a notable gap given that annotation value.

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 with the core capability and the return provenance front-loaded. The Chinese sentence largely restates the English one, which is mild redundancy, but it earns its place for a bilingual audience and adds nothing misleading.

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 a fully documented 5-parameter schema, an output schema, and annotations in place, the description only needs to frame the capability and result shape, which it does. The only shortfall is the absence of any guidance on query formulation or result volume, which would help an agent use it well.

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 100%, with every parameter (limit, query, date_from, date_to, visual_type) documented including the enum members. The description contributes no additional parameter meaning, so the baseline of 3 applies; the schema is doing all the work.

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 names a specific verb ('Search') and a concrete resource set ('indexed charts, tables, industry diagrams and research-relevant images') plus the provenance returned ('report/page provenance'). This clearly separates it from text-oriented siblings like search_research, search_filings and search_meetings, though those siblings are never named 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?

Usage is only implied by the resource type: an agent can infer it should call this when hunting for visuals rather than prose. There is no explicit when-to-use statement, no when-not-to-use, and no mention of alternatives such as search_research when the need is textual.

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