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

Annotations already establish read-only, non-destructive, idempotent, closed-world behavior, so the bar is lower. The description adds genuinely useful computation semantics beyond that: end-of-year discounting by default with a mid_year option, decimal rate convention, and an exhaustive enumeration of returned figures including the terminal value's share and the sensitivity grid — valuable given there is no output schema.

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?

A single long sentence plus a short rate-convention note; the core purpose is front-loaded and nearly every clause carries real content (input basis, output list, discounting convention). Dense and hard to parse in one pass, but there is little outright padding.

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 10-parameter nested calculator with no output schema, the description covers the two input pathways, the terminal value methods, discounting timing, and the full return set, which is the right information to surface. The remaining gap is around equity-bridge inputs (net debt, adjustments, shares) that affect the headline value and are only obliquely referenced.

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 50%, so the description must compensate, and it partly does: it explains that a year can give free_cash_flow or ebit with depreciation, capex and nwc_change (requiring tax_rate), the growth-vs-exit-multiple terminal choice, mid_year, and the sensitivity grid. It adds no meaning for shares, net_debt, currency, or adjustments, leaving several undocumented parameters unaddressed.

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+resource (discounted cash flow valuation) and the exact input basis: free cash flows or EBIT/depreciation/capex/NWC plus a WACC with a terminal value. It is unmistakably distinct from valuation_wacc or valuation_multiples by describing the full DCF mechanics, but it never explicitly names those siblings or says which to pick.

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 implies when it applies (you have forecast cash flows and a WACC and want enterprise/equity value per share) and notes it is free, but gives no explicit when-to-use versus valuation_wacc, valuation_multiples, or valuation_lbo, and no prerequisites or exclusions. Usage is inferable from the input contract rather than stated.

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