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

Annotations already provide readOnlyHint/idempotentHint/destructiveHint, so the bar is lower. The description adds meaningful behavioral context: that the tool 'computes your assumptions, it does not endorse them,' that output is arithmetic only, and that DCF results are highly sensitive to discount and terminal rates. It communicates the tool's non-authoritative, calculation-only nature well.

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 tightly organized into three paragraphs: what it does, when to use it (with sibling differentiation), and a caveat paragraph. Every sentence earns its place — no fluff, no repetition of schema fields. It's front-loaded with the core purpose.

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 6-param computational tool with 100% schema coverage and no output schema, the description is complete. It explains the calculation model (two-stage, Gordon Growth terminal), the purpose of each input relationship (discount rate above terminal rate is already in schema), and what outputs to expect. The sensitivity caveat is appropriate context for a tool whose results are assumption-dependent.

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 all six parameters are documented in the schema. The description adds framing beyond the schema: it explains how cash flow grows (stage-one years then forever at terminal rate via Gordon Growth Model) and notes the output uses the supplied price for margin of safety. This supplements the schema rather than repeating it, though the schema already carries a heavy load.

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 identifies the tool as running a two-stage DCF on user-supplied numbers, returning fair value per share, margin of safety, and terminal-value share. It names the specific verb ('Runs'), the resource (DCF), and the substantive outputs, which clearly distinguishes it from sibling valuation 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?

The description is exemplary here. It explicitly states when to use ('when the user wants to value a company under their own assumptions, test sensitivity, or check arithmetic') and explicitly names the alternative (get_stock_valuation) with a clear when-not-to-use and rationale for why the two won't agree. This is the best kind of usage guidance.

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