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

The description confirms the tool is not idempotent ('writes a new idea each call') and explicitly states 'Not read-only; it writes a new idea each call'. The annotations already set readOnlyHint=false, destructiveHint=false, so the description adds value by disclosing the non-idempotent behavior. It could mention if it requires authentication, but given annotations are present, this is well-handled.

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 three sentences long with no filler. It front-loads the core verb ('Create...'), follows with context vs sibling tools, then gives post-creation guidance. Every sentence adds value, and it is efficient for an AI agent to parse.

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 the tool has 5 parameters (2 required, 2 enums) and an output schema that would cover return values, the description sufficiently explains the core behavior, entry-point role, and next steps. The mention of 'request_revalidation' as a follow-up adds completeness. It doesn't elaborate on error handling or defaults (e.g., visibility default), but those are in the schema. A slight deduction for not addressing how the output schema ties in.

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 100%, so the schema already documents all parameters well. The description mentions 'title and description' but doesn't add semantic detail beyond what's in the schema (e.g., no explanation of trendId linking, ideaType categorization, or visibility options). Baseline 3 is appropriate since schema covers the parameters completely.

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 uses the verb 'Create' with the resource 'brand-new startup idea' and specifies the inputs 'title and description'. It distinguishes itself from the sibling 'claim_idea' by explicitly stating 'rather than claiming one', making the purpose unambiguous.

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 explicitly states this is 'the entry point for building an idea from scratch' and provides clear post-creation guidance: 'run validation (for example request_revalidation) to get a VC score'. It also distinguishes from alternatives by highlighting it's 'not read-only' and 'writes a new idea each call', which helps agents decide when to use it.

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