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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds useful non-structured context: the safe-harbor methodology, the due dates, and that it returns per-date amounts with past-due status plus a calendar file and PDF worksheet. However, it does not address the implicit side effect that generating a calendar file/reminders may write an artifact, so it stops short of full disclosure for a read-only-annotated tool.

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?

Front-loaded correctly with the 'Use this when' trigger and ends with scope limits, so the agent gets the gating information first. It is dense and somewhat overstuffed with quoted user utterances and a long computation clause, but nearly every clause carries selection or scope information, so the length is largely justified.

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 26-parameter tool, the definition covers triggers, methodology, output artifacts and explicit exclusions, and an output schema exists so return shape need not be repeated. Nothing an agent needs to decide whether and how to call it is missing.

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 description coverage is 100% across all 26 parameters, so the schema already carries the parameter burden and baseline 3 applies. The description adds the overall calculation model (90% vs 100%/110% safe harbor, $1,000 rule, withholding substraction) which helps an agent know which inputs matter, but it names no individual parameter or format guidance beyond what the schema states.

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 (plan quarterly estimated tax payments) plus the exact computation it performs: compares 90% of the 2026 estimate with the 2025 tax, subtracts withholding and payments made, applies the $1,000 rule. It also names out-of-scope actions (paying the IRS, logging into tax software) and neighbors (due-date lookup, SE tax) implicitly, so an agent can distinguish it from siblings without opening a schema.

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?

Opens with an explicit 'Use this when' clause that quotes the user phrasings that select this tool, including the W-2-plus-1099 case and the missed-payment catch-up case. It closes with explicit exclusions ('Do not use for paying the IRS online or logging in to tax software') and limits (federal only, no penalty amount, no tax advice), giving both when and when-not.

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