fiscal_calendar

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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), and the description adds substantial behavior on top: how dueDate is shifted for weekends and Romanian legal holidays, what each status value means (filed requires a submitted/accepted declaration of that type for the period), which company settings (vatPeriod, incomeTaxPeriod, hasEmployees via companies_update) drive the rules, and what allCompanies changes.

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?

Purpose is front-loaded in the first clause, and with no output schema the long item-field enumeration does real work rather than repeating structured data. It is still a single dense paragraph with nested parentheticals that could be split into a return-shape list for faster scanning.

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?

No output schema exists, so the description must carry the return shape — and it does: every item field (code, label, dueDate, nominalDueDate, daysLeft, period, appliesBecause, declarationType, status, dosarId/dosarTitle) is explained, along with the code catalog and the null cases for declarationType. For a read-only, 4-parameter, no-pagination tool this is complete enough to call correctly.

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 days/from/companyId/allCompanies are already documented in the schema, including defaults and the 366 cap. The description restates the same defaults and adds the accountant-view framing for allCompanies, but says nothing about companyId's env-var override, so it adds little beyond the structured field docs.

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 precise verb+resource+scope: filing deadlines for the next `days` days plus unfiled ones from the last month. It also routes to a sibling by noting declarationType is 'the type to pass to declarations_create', though it never contrasts itself with declarations_list or expiries_upcoming, so differentiation is inferred rather than stated.

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?

Usage context is clear: use it to see what is due in a window plus what was missed last month, and use allCompanies=true for the accountant view across every visible company. There is no explicit when-not guidance or named alternative for the case where the agent wants all declarations rather than deadlines.

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