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

Annotations already declare non-readonly, non-idempotent, non-destructive, closed-world. The description adds substantial context beyond that: it does not start watching by itself, it returns a consentUrl requiring user-side e-mail confirmation, unconfirmed drafts expire in 24 hours, matching is limited to AutoIsto CZ listings and may be incomplete. Not a 5 only because retry/duplicate behavior for repeated calls is not addressed.

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 and trigger first, then the consent/security procedure, then parameter notes and coverage caveat. Every sentence carries a distinct rule, though the safety-instruction block is long enough that the parameter guidance arrives late.

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 mutation-style tool with an output schema, this covers everything an agent needs: what is created, what is returned (consentUrl, intentCode), what the user must do next, expiry, privacy of hiddenLimitCzk, and the aggregator coverage limitation. Nothing essential 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 the baseline is 3, but the description adds real meaning: statement must be a short Czech/Slovak phrase with CZK prices, buyBy ends watching, hiddenLimitCzk is stored encrypted and never shown or returned and should only be passed if the user stated it. niceToHave is not explicitly distinguished from a filter in the description, though the schema covers it.

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+resource (start watching Czech car listings on behalf of the user) plus the trigger condition, and explicitly names the sibling intent_list_matches for reading results. An agent can distinguish this from intent_withdraw_intent / intent_get_intent 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?

Gives an explicit when ('user asks AutoIsto to keep watching ... over time') with a concrete example, plus hard when-not rules: never ask for the e-mail, never open the link, don't pass hiddenLimitCzk unless the user said it. It also routes to the alternative reader tool with the returned intentCode.

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