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

Annotations already declare readOnly, idempotent, non-destructive and closed-world. Beyond those, the description adds the return format (markdown, token-efficient), the image/status edge case, and a scope requirement ('Scope view'), which are useful behavioral details not covered by the annotations.

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?

Compact and front-loaded: the core fetch action and format lead, followed by parameter provenance and the image exception. Every sentence carries information, with no 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?

With no output schema, the description correctly notes the return type (markdown), which the agent would otherwise lack. Combined with the annotations covering safety and the sibling routing for the image case, it 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?

The schema has 0% description coverage and does not explain the single integer parameter. The description compensates by stating what policy_id is and its provenance ('från list_policies'), which is meaningful guidance beyond the bare schema.

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 (hämta/read) and resource (policydokument/underlags innehåll) and specifies the output format (markdown). It also names the sibling it is not when the content is an image, letting an agent distinguish it from read_underlag_image without opening either 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 when-to-use context (policy_id comes from list_policies) and an explicit when-not-to-use rule with the alternative: if the entry's status is 'image', use read_underlag_image instead. 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.