generate_report

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

The description richly discloses behavior beyond the sparse annotations (readOnlyHint=false, idempotentHint=true). It reveals the renderer's visual distinction for ai_interpretation sections, the mandatory 'not advice' disclaimer, and the style/voice contract for section writing. No contradiction with annotations — the deterministic assembly described is consistent with idempotentHint=true.

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?

Well front-loaded: purpose first, then usage timing, then metadata behavior, then voice requirements. Every sentence earns its place — the style guidance with anti-pattern examples materially affects output quality. It runs somewhat long (~150 words), but the density of operational guidance justifies the length.

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?

Comprehensive for a complex tool with 10 params and no output schema: it covers purpose, workflow timing, metadata semantics, rendering behavior, and writing style. Gaps are minor — no explicit return-value statement (though the 'report envelope' implies it) and no routing among the report-generating siblings.

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 schema coverage at 50%, the description compensates on the most complex parameter: it explains the sections structure (summary, tables, citations, confidence) and the special metadata.kind = 'ai_interpretation' value with its rendering implications. The simpler display parameters (title, subtitle, brandName, classification) are covered by the schema's own descriptions, so the partial coverage gap is acceptable.

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: 'Assembles a structured research report from ResearchSections... into the standard report envelope.' The 'does no research of its own' boundary separates it from the research-gathering siblings. However, it does not explicitly distinguish itself from the three report-generation siblings (generate_institutional_report, generate_markdown, generate_pdf), which is a differentiator gap.

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 clear sequencing: 'Use after gathering facts with other tools; this tool does no research of its own.' This tells the agent when in the workflow to invoke it. However, with three other report-generating siblings present, it offers no routing guidance on when to choose this tool over generate_institutional_report, generate_markdown, or generate_pdf — an explicit exclusion would push this to 5.

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