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

Annotations already provide readOnlyHint=true, idempotentHint=true, and openWorldHint=false, but the description adds valuable details: it withholds 'stale, future, uncovered or unconverted venue estimates' and 'Fees excluded'. These specifics about data filtering and fee handling go beyond the annotations and inform the agent about the tool's behavior.

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 two sentences, front-loaded with the core action and then conditions/caveats. Every phrase adds value: the compare scope, the filtering behavior, the fee exclusion, and the research-only caveat. No wasted words, highly efficient.

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 simple tool with 2 optional parameters and no output schema, the description covers the purpose and key behavioral constraints. However, it does not describe the response format (e.g., what the comparison result looks like) or how the rungs/brackets classification appears in output, leaving some uncertainty for an agent expecting a concrete return value.

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?

With 0% schema description coverage, the description must explain the parameters. It maps sizes_usd to 'up to four BTC sell sizes' and implies max_age_seconds through 'freshness' and 'stale' references. However, it doesn't explicitly name the parameters, explain units, or clarify how 'brackets' vs 'exact rungs' relate to input values. It partially compensates but leaves ambiguity.

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 states the tool compares up to four BTC sell sizes, with specific comparison modes ('exact rungs, brackets or out-of-range') and explicitly excludes certain data ('stale, future, uncovered or unconverted venue estimates'). It also clarifies it is 'research only, no trade clearance', distinguishing it from execution tools and siblings like exit_cost or trade_safety_exit_context.

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?

It says 'research only, no trade clearance', which tells the agent not to use it for trade execution, and implies it is for analyzing exit sizes. However, it does not explicitly compare with sibling tools (e.g., exit_cost for cost analysis, trade_safety_exit_context for safety), nor does it give clear 'use this when...' guidance. Usage context is inferred rather than stated.

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