Valuation Core

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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, but the description adds genuinely new behavioral facts: deterministic computation, no external calls, no authentication, and that unsupported fields return an error envelope rather than raising. The only weak point is the unexplained 'shared result envelope', which is vague despite an output schema existing.

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 routing constraint and safety profile are front-loaded, and the sentences are mostly information-dense. Minor redundancy ('a startup valuation valuation capability', restating 'valuation_core' twice) costs it a point, but nothing is padded with filler.

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 thin dispatcher wrapper over an underlying schema, the description covers the essentials: purpose, routing, error behavior, and safety, and an output schema exists so return values need not be explained. The undefined 'shared result envelope' reference and the missing pointer to the actual underlying schema for supported fields leave a small gap.

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?

There is a single 'arguments' parameter at 100% schema description coverage, so the schema already carries the load and a 3 is the baseline. The description adds only marginal value by noting the object must match the underlying tool's schema and that unknown fields error out rather than being silently ignored.

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 names a specific verb+resource (startup valuation computation) and explicitly frames itself as the fallback dispatcher alongside named native tools. It distinguishes itself from siblings by listing the tools it should not replace. The phrasing 'the startup valuation valuation_core case' is somewhat circular and the duplicated word 'valuation valuation' muddies the statement, keeping it below a 5.

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?

It gives explicit when-to-use ('only for the startup valuation case the native tools do not handle'), when-not ('prefer the native tool whenever it applies'), and enumerates six concrete alternatives (valuation_dcf, valuation_nav, valuation_cca, calculate_wacc, calculate_ecl, black_scholes_price). Routing is fully specified with no inference required.

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