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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description discloses meaningful behavioral details: it never raises a protocol error but returns a structured error object, it is read-only and idempotent, and it explains the matching algorithm with tolerances and lot summation. These details give an agent accurate expectations for execution and retry.

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 dense but every section earns its place: purpose, example input/output, matching rules, usage trigger, error behavior, and safety guarantee. It is front-loaded with the core purpose and organized so an agent can quickly extract the key information.

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 reconciliation tool with matching logic, tolerance parameters, and error handling, the description covers all critical aspects: input source, return categories, matching criteria, error format, retry safety, and a non-substitute caveat. An agent has enough context to invoke the tool correctly and interpret results.

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% and the schema already describes each parameter. The description adds value with a realistic input example, clarifies that basis may be blank, explains that tolerances govern matches, and notes that disposals come from build_lots. This goes beyond a baseline but does not need to fully compensate since the schema is strong.

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 opening sentence 'Diff the broker's 1099-DA lines against the computed disposals' names a specific verb, resource, and operation. The tool is clearly distinguished from siblings like build_lots and form_8949_rows by its reconciliation role and the explicit 'Use when the form arrives...' trigger.

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 gives a concrete use case: 'Use when the form arrives and the basis column is blank for coins that came from your own wallet.' It also warns 'Not a substitute for the broker's statement.' However, it does not explicitly name alternative sibling tools or state when not to use this tool, so it stops short of full when/when-not guidance.

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