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 profile is covered. The description contributes real behavioral context beyond that: results are computed at list price, and the math plus a dated price file match the public modevc.com calculator, signalling deterministic parity rather than live market pricing. It does not state what the returned object looks like, but with no output schema an enumeration of computed figures partially covers that.

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?

Two sentences, front-loaded with the verb and the headline outputs, mapping closely to what the tool returns. The output enumeration is long but each item earns its place; the trailing "compares 9 common models" fragment is the only weakly justified clause and is arguably inconsistent with the enum.

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?

With 10 optional parameters and no output schema, the description carries the burden of telling an agent what comes back, and it does so by listing all five result families. What's missing is shape-level detail, such as whether margin output includes a break-even price per user or how savings are broken out, which matters for a calculator with no declared return type.

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 the baseline is 3 and the schema already explains each parameter, including defaults. The description adds directional meaning by naming prompt-cache savings and routing a share of requests to a cheaper model, but it does not clarify inputs the schema leaves thin, such as the interaction between route_model and route_share_pct or how target_margin_pct changes the output. The odd claim "compares 9 common models" against a 20-value enum adds no usable parameter guidance.

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?

Opens with a specific verb ("Estimates") and enumerates the exact quantities produced: monthly LLM spend, cost per user and per request, prompt-cache savings, routing savings, and gross margin. It also scopes the domain to models from Claude, GPT, Gemini, DeepSeek and Grok, which cleanly separates it from the equity, dilution and SaaS-metric calculators in the sibling list.

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 phrase "for an AI product on any current Claude, GPT, Gemini, DeepSeek or Grok model at list price" gives a clear condition for reaching for this tool. It stops short of naming when not to use it or pointing at a sibling (e.g., a generic burn/SaaS calculator), so it sits just below the explicit routing seen in the strongest definitions.

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