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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description's extra burden is light — and it does add genuinely new context: the call is free and 'does not debit', and omitting both parameters falls back to the debiting catalog. It does not describe the shape of the estimate returned, which is the main residual gap.

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?

Three short sentences, each doing distinct work — purpose, parameter routing, and cost behavior — with the purpose front-loaded and no 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 two-parameter, annotation-backed read tool with no output schema, this covers the essentials: when to call it, how to fill each parameter, the no-parameter default, and the fact that it costs nothing. Only the return shape of the estimate is left implicit.

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 0%, so the description carries the full load, and it does: tool is an MCP name with a concrete example (angel_intelligence), endpoint is a REST name with a concrete example (angel-report), and omitting both selects the debiting catalog. It leaves one ambiguity unaddressed — what happens if both tool and endpoint are supplied.

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 and resource — 'Estimate credit cost' — with a scope qualifier ('before starting a run'). This cleanly separates it from sibling check_balance (which reads a balance rather than projecting a cost), though it does not name that sibling explicitly.

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?

Gives a clear triggering context ('before starting a run') and tells the caller what to do when no target is specified ('Omit both for the debiting catalog'). It stops short of naming alternatives (e.g., check_balance) or stating any when-not conditions.

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