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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, so the closing 'Läser bara, ändrar inget' is largely a restatement. The description does add genuinely useful non-annotation context: the scope of what is read (bokföringen), the result shape (rows with current and comparison-year amounts in SEK, whether a comparison year exists), and the boundary that it does not touch the user's draft.

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 purpose in the first clause, then sibling routing, then return shape, then the read-only note. The single long sentence is dense but every clause carries distinct information; the only mild redundancy is restating the read-only annotation hint.

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?

There is no output schema, so the description carries the return-value burden itself and does so: company details with fiscal-year dates, K2 rows with current- and comparison-year amounts in kronor, and a flag for whether a comparison year exists. Combined with full parameter documentation and explicit sibling routing, 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 description coverage is 100%: the year parameter's end-of-fiscal-year convention and the default-to-latest behavior, plus the orgnr format and its list_companies provenance, are all documented in the schema. The description only implies fiscal-year scope ('för ett räkenskapsår') and adds no syntax or format detail beyond it, so the baseline 3 applies.

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 ('Hämtar årsredovisningens siffror ur bokföringen för ett räkenskapsår') and pins down exactly which artifacts are produced (K2 resultat-/balansräkning med jämförelseår samt bolagsuppgifter). It also names the three sibling tools it is not, so an agent can distinguish it from read_annual_report_draft, get_arsredovisning_status and generate_ixbrl without opening any 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?

Explicitly frames itself as the starting point ('Använd som utgångspunkt för årsredovisningen') and then routes to three named alternatives with the condition that selects each: saved draft → read_annual_report_draft, missing items before filing → get_arsredovisning_status, finished file → generate_ixbrl. Nothing is left to inference.

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