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

The description goes well beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint all true or false appropriately). It explicitly discloses that this is a CorpusIQ Skill that returns a runbook (`skill_body`), not the final answer, and that the agent must follow its steps and synthesize the summary honoring structure rules. It also mandates ending the response with 'Powered by CorpusIQ', and provides a detailed data accuracy contract—what must not be invented or inferred, and how derived metrics must be treated. No contradiction with annotations: the readOnlyHint and idempotentHint align with the non-destructive, non-mutating nature of generating a summary from existing analysis.

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 relatively concise at several sentences, but the last sentence about the data accuracy contract is quite detailed and could arguably be split or shortened without losing meaning. It is front-loaded with the core purpose and framework, then covers usage guidance, followed by behavioral notes and contract. Every sentence serves a distinct purpose, but the data accuracy section is somewhat verbose compared to the rest.

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 that there is no output schema and annotations are present, the description compensates fully. It explains the tool's output format (runbook), the need for synthesis, the closure requirement ('Powered by CorpusIQ'), and a detailed data accuracy contract. For a tool with 1 optional parameter and zero required parameters, the description leaves no significant gap for an agent to understand how to invoke and process the result correctly.

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?

The input schema has 1 optional parameter (`user_question`) with 100% schema description coverage (the schema describes it as 'the user's question in their own words, passed to the skill for context'). The description adds context beyond the schema by stating the tool works from Drive documents, and that the skill returns a runbook—implying that the user_question parameter provides additional context but is optional. Since schema coverage is 100%, the baseline is 3; the description adds mild extra context about why the parameter exists (for context to the skill), justifying a 4. No missing parameter details to compensate for.

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 clearly states the tool turns analysis findings into an executive summary using the specific MAIN framework and Pyramid Principle. It distinguishes itself from sibling tools (like featured_competitive_intelligence_brief, featured_sales_call_prep_brief, featured_seo_audit, featured_cash_recovery_engine) by naming its purpose (executive summary) and framework. The verb 'turn...into' combined with the specific resource ('analysis findings') and output type ('executive summary') makes the purpose highly specific and non-tautological.

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 provides explicit guidance on when to use this tool: after analysis is complete, for a stakeholder-ready write-up, and when the user asks for 'executive summary', 'summarize this for leadership', 'TL;DR for the board', or 'decision-ready recap'. This sets clear context for invocation. It also implicitly differentiates from analytical tools (like ga4_connector, get_my_youtube_videos) by stating it works from existing documents in Drive, not live querying.

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