AutoIsto — car watch

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world behavior, so the safety profile is covered. The description adds genuine context beyond that: the set of lifecycle states it can report and a privacy guarantee that only the statement and dates are returned, never e-mail, the hidden limit, or other personal data.

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?

Two sentences, front-loaded with the action and the state enumeration, followed by the input requirement and the return/privacy constraint. No filler and nothing repeated from the schema.

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 single-parameter, idempotent read with an output schema, the description covers purpose, the trigger condition, the possible states, and the privacy boundary of the response. Since an output schema exists it need not enumerate return fields, and nothing an agent needs 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%, and the single intentCode parameter is already documented as 'the intentCode returned by intent_publish_intent'. The description only restates that the code is required, adding no format, pattern, or sourcing detail beyond the schema, 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+resource (fetch the state of an intent) and enumerates the concrete states returned (confirmed/active, waiting, expired, withdrawn). It also names the sibling that creates the intent (intent_publish_intent), so an agent can place it in the lifecycle without opening another 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 the use case: check whether an intent published via intent_publish_intent has been confirmed. That is clear context for when to call it, but it never names the remaining alternatives (intent_withdraw_intent, intent_list_matches) or states when not to use this tool, so it stops short of full when/when-not routing.

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

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

Goes well beyond the annotations (which only cover read-only/idempotent/no-destructive semantics) by disclosing the 20-match cap, that the server cannot post into the conversation, that results are aggregator-scoped and may be incomplete, and that cars may already be sold. These are exactly the operational caveats an agent needs before presenting results to a user.

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-loads the usage trigger and then layers constraints in a single dense paragraph with no filler sentences. It is slightly long for a two-parameter list tool, but each clause carries distinct information.

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?

Although an output schema exists, the description usefully summarises the shape of results (newest 20 with price, verdict and link) and closes the main gaps an agent would otherwise hit: empty results before confirmation and aggregator-driven incompleteness. Nothing needed to call and interpret this tool 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%, and both the intentCode requirement and the 'since' semantics are already documented in the schema. The description restates them ('requires the intentCode; optional since returns only newer matches') without adding format or edge-case detail beyond the schema, so the baseline of 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 ('list cars found for a car watch') and ties it to the intent created via intent_publish_intent, which cleanly separates it from the sibling read tool intent_get_intent and from publish/withdraw. An agent can identify what this returns without opening the 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 trigger ('use this when the user asks what AutoIsto has found') plus a precondition ('before the user confirms the intent there are no matches'), which tells the agent when NOT to expect results. It also names intent_publish_intent as the originating tool, so the workflow position is unambiguous.

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

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

Goes well beyond the annotations: two-step consent flow via consentUrl on www.autoisto.sk, prohibition on asking for or handling the user's e-mail, opening the link, 24-hour expiry of unconfirmed drafts, e-mail delivery of matches, and encryption of hiddenLimitEur. Annotations only say it is non-read-only and non-idempotent, so this added operational detail is exactly what the description must supply.

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 the use case, then the consent mechanics, then optional-parameter guidance and coverage caveats. Despite being long, every sentence carries an actionable constraint and none is redundant 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?

For a 4-parameter tool with an output schema, this covers everything the agent needs: when to call it, what it returns (consentUrl, intentCode), what the agent must not do, how long an unconfirmed draft lives, and the data-coverage limitation of an aggregator.

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 already 100%, so the baseline is 3, but the description adds genuine meaning: hiddenLimitEur is optional, must be passed only if the user volunteered it, is stored encrypted and never surfaced to sellers or any tool, and buyBy stops the watch. It also frames statement/niceToHave semantics (required match phrase vs. non-filtering wishes) that go slightly beyond the schema wording.

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 action (create a standing watch request for car listings) with the domain spelled out (Slovak listings, AutoIsto, EUR) and a concrete example. It is unmistakably distinct from the sibling read/withdraw tools intent_get_intent, intent_list_matches and intent_withdraw_intent.

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 gives the trigger condition ("when the user asks AutoIsto to keep watching ... over time") with a sample utterance, states what the tool does not do (does not start watching itself), and routes the agent to intent_list_matches with the returned intentCode for reading results.

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

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: the effect is immediate and no further e-mails are sent for the intent. It stops short of clarifying whether the intent record itself is deleted or only the watch is withdrawn — relevant given the destructiveHint.

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 short sentences, front-loaded with the usage trigger and followed by effect and required input. Nothing is padded, though the trailing 'Requires the intentCode' sentence largely duplicates schema information.

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?

An output schema exists, so return values need not be described, and the single parameter is fully covered in the schema. The description supplies the trigger, the effect, and the required input, leaving only the delete-vs-unwatch distinction unspecified.

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%, so the intentCode parameter (pattern, origin) is fully documented in the schema. The description only restates 'Requires the intentCode' with no added format or sourcing detail beyond the sibling reference. 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 ('stop watching for an intent') and ties it to the originating sibling intent_publish_intent. An agent can distinguish this reverse operation from intent_get_intent / intent_list_matches 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?

'Use this when the user wants AutoIsto to stop watching for an intent created with intent_publish_intent' gives an explicit trigger condition and anchors it to the sibling that creates the watch. No when-not guidance is given, but the pairing with intent_publish_intent is unambiguous.

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