generate_institutional_report

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

The annotations only carry readOnlyHint=false, openWorldHint=true, idempotentHint=false, leaving the description to carry the behavioral burden, and it does so thoroughly. It discloses the sector fallback, the report's closing section telling the calling model exactly which analyst-judgment sections to add next (SWOT, bull/bear, valuation with metadata.kind='ai_interpretation'), the risk screen's evidence checklist of which sources were checked, output rendering behavior, and the required writing convention with concrete examples of direct versus hedged phrasing.

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 unusually long for a tool definition at roughly 200 words, but nearly every clause earns its place: the verb+scope statement is front-loaded, the consolidation directive over nine sibling tools is placed early, and the trailing writing-style instruction, while lengthy, dictates the model's output voice and is essential to downstream quality. 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?

For a complex 7-parameter aggregator with no output schema, the description covers a great deal: the report's section composition, sector fallback, output formats, sibling alternatives to avoid, and the expectation that the calling model adds analyst-judgment sections. What is missing is the response shape (no output schema exists, and the description only says 'rendered in the requested output formats') and the behavioral meaning of the three enum parameters, both of which matter for a correct call.

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 57%: company, sector, companyDomain, and outputFormats already have schema descriptions, and the tool description adds no new per-parameter meaning — the sector fallback repeats the schema text and outputFormats merely lists the same formats. The three enum parameters (listed, country, reportType) remain undocumented in both schema and description, so an agent has no way to know what reportType=debt_raising changes or what listed=unlisted affects behaviorally. Since coverage sits in the mid range and the description does not compensate for the enum gaps, baseline 3 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 opening clause 'Generates a complete institutional research report for a company in one call' pairs a specific verb with a clear resource, and the description then enumerates the report's contents (company profile, financial snapshot, macro/industry overview, competitor list, funding history, risk screen, news). It differentiates itself from siblings by explicitly naming the nine tools it consolidates, so an agent can select it over search_company or company_profile without ambiguity.

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 contains an explicit directive: 'Use this instead of calling search_company, company_profile, financial_statements, discover_competitors, litigation_history, promoter_background, negative_news, latest_news, and generate_pdf separately,' which clearly states when this tool is the right choice and names the alternatives. It also explains the sector fallback behavior. It stops short of a full 5 because it never states when NOT to use it — e.g., when only a single section like financial statements is needed — but the consolidation guidance is strong.

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