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

Annotations already cover read-only/idempotent/non-destructive, and the description goes well beyond them: it discloses the data provenance (RIK monthly extracts of e-Business Register filings) and a behavioral quirk that matters for interpretation — some reports have metadata but null figures, so a row can answer with nulls rather than erroring. That is exactly the additional context annotations cannot carry.

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 resource definition and the 'NOT full reports' boundary, then the usage modes, then the edge case. It is a dense single paragraph with long enumerations, but essentially every clause earns its place and nothing is filler.

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 carries the return-value burden and does: it enumerates the list-mode fields (submission date, audited flag, filer-size category) and the year-mode figures (revenue, profit/loss, assets, equity, FTE employees, EMTAK sales breakdown), plus the null-figure case. Nothing needed to call it correctly 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 coverage is 100%, so baseline is 3; the description adds genuine semantic meaning by explaining that omitting year switches the tool into a list mode and that supplying year switches it to a figures mode. That mode-switch behavior of an optional parameter is more than the schema's 'omit to list every year' phrasing conveys on its own, though the field-by-field return mapping is somewhat redundant.

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 resource (Estonian annual-report financial indicators from RIK's open-data extracts) with a verb-like scope, and explicitly bounds it with 'NOT full reports', which separates it from siblings like ee_company or company_facts. An agent knows exactly what comes back before opening the 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?

Gives explicit mode selection: 'Pass registry_code alone to list every year... add year for that year's figures', which is real when-to-use guidance tied to parameters. It stops short of naming a sibling alternative (e.g. ee_company for register identity data), so it is clear context without explicit exclusion routing.

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