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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety bar is already met. The description adds genuine context beyond them: deterministic computation, no external calls, no authentication, and the error contract that unsupported fields return an error envelope rather than raising. It does not describe runtime cost, result envelope shape (though an output schema exists), or any limits.

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?

Compact and front-loaded: the identity, routing rule, safety profile, and error behavior each appear once in a logical order. The only waste is the duplicated 'valuation valuation' phrasing and the slightly padding 'exposed through this server so one endpoint covers corporate, startup, and intangible valuation' clause.

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?

An output schema exists, so return values need no explanation, and the auth/safety/error behavior is fully covered. The remaining gap is substantive: for a tool whose name is unrecognizable ('hardware'), the description never says what domain inputs or outputs distinguish it from the ~35 valuation siblings, leaving the routing decision under-specified at the exact point it matters.

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 passthrough 'arguments' object, whose schema definition already points the caller to the target tool's schema (100% coverage). The description reinforces this ('pass an arguments object matching that tool's schema') and adds the valuable failure semantics that unsupported fields yield an error envelope. For an inherently opaque forwarding parameter this is about as much as can be said.

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 identifies the resource as a 'startup valuation valuation_hardware capability' but never explains what hardware valuation actually computes, and the phrase 'valuation valuation' is a redundant restatement of the name. It does route the agent away from named siblings, which helps, but the core purpose stays opaque — an agent learns it is a valuation endpoint, not what it produces.

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?

Explicitly says to use it 'only for the startup valuation valuation_hardware case that the native tools do not handle' and lists the preferred alternatives (valuation_dcf, valuation_nav, valuation_cca, calculate_wacc, calculate_ecl, black_scholes_price). That is clear when-to-use guidance. It loses a point because the selection condition is circular — 'the case native tools do not handle' is never defined by any observable input or output characteristic.

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