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 covered. The description still adds real value by disclosing the return content: amounts in whole kronor, which accounts each box derives from, suggestions for specific boxes, accounts lacking a box, and error/warning checks plus whether the file can be downloaded.

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?

Dense and front-loaded: purpose first, then the enumerated content, then the scope constraint and arguments. The trailing 'Scope view. Argument: orgnr, year.' fragments are terse and slightly jargon-y but consume minimal 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?

With no output schema, the description carries the burden of describing return values and does so thoroughly (boxes, amounts, account mapping, suggestions, checks, download flag). The only meaningful gap is the undocumented 'year' parameter semantics, which matters because fiscal-year selection drives the result.

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 50%: orgnr is well documented in the schema (10 digits, optional hyphen, get via list_companies), while year is bare. The description only says 'Argument: orgnr, year' and implies fiscal-year semantics via 'för ett räkenskapsår', which adds a little meaning but no format or range guidance for year.

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 ('Läser NE-bilagan (enskild firma) för ett räkenskapsår') and enumerates the content produced (boxes B1-B16, R1-R48, amounts, underlying accounts, suggestions, checks, downloadability). This clearly separates it from mutation siblings such as set_ne_bilaga_inputs, prepare_bilaga and mark_ne_submitted.

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?

It gives an applicability constraint ('Gäller bara enskild firma') which functions as a when-not condition, but it never names the alternative tools (set_ne_bilaga_inputs for editing, prepare_bilaga for generation) or states what to do for a non-sole-proprietorship company. Usage is implied rather than routed.

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