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

Annotations already declare readOnlyHint, openWorldHint and destructiveHint=false, so the safety profile is covered structurally. The description adds genuine extra context the annotations lack: the 2022-09-01 data cutoff, the error surfaced when the account has no Reports, and the required Cotlet API key with app access.

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 opening fragment 'Joist: A Joist report for a date range: revenue, invoices, estimates or sales tax.' is immediately redundant with the following sentence, which repeats the same date-range and report-type enumeration. The remaining sentences are dense and earn their place, but the lead wastes space.

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 read-only reporting tool with no output schema, the description does the needed work: it says what data comes back per report type, the historical coverage limit, the error case, and the auth prerequisite. Nothing essential is missing, though return format/pagination detail is absent.

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%, so the baseline is 3, but the description goes further by explaining what each enum value actually returns ('revenue received (partial payments included)', 'sales tax collected by jurisdiction') and clarifying the client parameter scopes results to one client by name — semantic value the bare enum does not carry.

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 ('Returns one of Joist's Reports') and enumerates the four report types with what each contains (revenue received incl. partial payments, invoice balances/statuses, estimate volume/statuses, sales tax by jurisdiction). It does not distinguish itself from sibling retrieval tools such as joist_export_documents or joist_list_invoices, so it stops short of a 5.

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 clear triggering context: a date range is required, an optional single-client filter is available, and it discloses a hard data boundary ('reports only include data entered after 1 September 2022'). It does not name alternatives or say when not to use it, which keeps it from a 5.

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