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

Goes well beyond the annotations (readOnlyHint=false, idempotentHint=false) by disclosing what actually happens: per-pattern clamping to maxima, red-flag penalties capped at 15, exact verdict thresholds (Mediocre <55, Not sure 55-74, Fertile soil 75+), persistence, and sanitization of free-text links. This is unusually rich behavioral context for a mutation tool.

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-loads the purpose and packs verdict thresholds, penalty caps, and sanitization into one dense but mostly waste-free sentence. The single run-on structure is slightly crowded, but every clause carries information an agent needs.

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, non-idempotent write tool with no output schema, the description covers the return (report_id + shareable link), the storage side effect, scoring rules, and sanitization. It is nearly complete, with the main gap being the unaddressed parameters from the 46%-covered schema.

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 only 46% across 13 parameters, so the description should compensate but only partially does — it clarifies that all 10 pattern ids must be passed and explains the red-flag penalty cap, but leaves website, working, reframes, interview, risks, assumptions, confidence, and venture_note unexplained. Marginal value over 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 (totals/computes a scorecard), names the exact resource (startup idea scorecard), and enumerates the mechanics (clamps patterns, applies penalties, sets verdict, stores, returns report_id + link). It also names the sibling rubric tool it consumes, so it is clearly distinguishable from the other score_* tools.

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?

Implies a clear workflow — write the scorecard using the rubric from get_startup_validator_rubric, then call this to total it — and gives the operational rule 'Pass all 10 pattern ids.' It lacks any explicit when-not or alternative-selection guidance, but the dependency on the sibling tool provides solid context.

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