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

Adds substantial behavior beyond the annotations (readOnlyHint=false, idempotentHint=false, openWorldHint=true): no mail is sent until explicit user confirmation, logged-in calls produce a draft requiring confirm_action approval, and the email is sourced from the account rather than the argument. This is exactly the mutation-specific context the annotations cannot convey.

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?

Three dense sentences, front-loaded with the action and effect, then the consent precondition, then the OAuth/confirm_action flow. Every sentence earns its place, though the final sentence packs two distinct facts (draft state and email source) that could be split.

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?

For a non-idempotent mutation with no output schema, the description covers consent, double opt-in, the confirm_action hand-off, and email sourcing. Remaining gaps are the unmentioned drivmedel filter and what the call returns (e.g., a draft identifier), which an agent would benefit from before invoking.

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 0% and there are 6 parameters, so the description must carry the load. It clarifies email (taken from the OAuth account), samtycke (explicit consent), and maps price/brand/free text to matching criteria, but never mentions the drivmedel enum (el/bensin/diesel/laddhybrid/hybrid) and leaves maxPerManad's meaning (max price per month?) ambiguous.

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 ('Skapar en bevakning') plus the concrete effect: the user receives email about new campaigns matching price, brand, or free text. It also explains the form the call takes under OAuth (a draft), which no sibling does, so an agent can tell it apart from confirm_action and list_campaigns.

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 an explicit precondition and instruction ('Kräver e-post och uttryckligt samtycke – fråga användaren innan du anropar') and describes the double opt-in gate plus the OAuth draft -> confirm_action path. It does not contrast against non-watch siblings such as list_campaigns, so it stops short of the full when/when-not/alternatives bar.

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