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 fully covered. The description adds genuine context beyond that — rows carry an IRS source URL and a checked date, and the response includes the dataset page URL and license — but is silent on truncation behavior when limit is hit or on what happens with unknown filter keys.

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 with the core action, then the dataset enumeration, then response contents — a sensible order with no filler sentences. The inline parenthetical dataset list is somewhat dense but each element is load-bearing.

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 a full input schema and an output schema present, return-value detail is largely redundant, yet the description correctly orients the agent to provenance fields. The remaining gap is that filterable column names are knowable only by trying, which matters for a tool whose main optional capability is filtering.

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%, so the schema already documents slug, limit, and filters including the substring vs exact-match semantics and the example. The description only restates 'filter by column values' and adds no information about which column keys actually exist per dataset, which is the one thing the schema cannot tell the agent.

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 and resource ('Returns rows from the datasets published by ProfitDrawer') and enumerates exactly which datasets are covered. An agent knows precisely what it retrieves, though it doesn't distinguish this from adjacent retrieval siblings like get_answer or search_profitdrawer.

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?

States that filtering by column values is optional, which implies the retrieval-vs-filtered-retrieval usage pattern. It gives no explicit when-to-use guidance, no conditions that would favor search_profitdrawer or get_answer, and no exclusions.

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