NaKus unit price

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds useful behavioral context: it returns only the URL rather than price data, requires an exact slug, and should not be used for quoting. It does not describe failure behavior for a bad slug, which keeps it short of a 5.

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?

The output type and format are front-loaded in the first clause, followed by usage conditions, prerequisites, exclusions, and safety traits. Every sentence adds a distinct decision-relevant fact 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?

For a single-parameter, read-only URL-returning tool with no output schema, the description supplies the return format, the precondition, the discovery alternatives, and the boundary against get_unit_price. Nothing needed to select or invoke 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 coverage is 100%, including the example 'persil-color-gel-100-prani', so the schema already carries the baseline semantics. The description adds meaning by emphasizing that the slug must be exact and by naming search_cite_answers and get_unit_price as discovery paths, which goes beyond the schema text.

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?

The description states a specific verb and resource: return the 1200×630 PNG price-card URL for a Cite answer. It explicitly distinguishes the output from JSON price fields and from get_unit_price, so an agent can identify the tool without inspecting 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?

It gives explicit when-to-use guidance ('when the agent needs an image, not JSON price fields') and when-not-to-use guidance ('does not replace get_unit_price for quoting €/unit or buy_url'). It also names the sibling tools for discovering the required slug, leaving no routing ambiguity.

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 cover read-only, idempotent, and open-world, so the redundant 'Read-only, idempotent' line adds nothing. What does add value is the output-construction rule (buy_url always nakus.sk/out/?src=ai, never raw merchant or Heureka) and the brand disambiguation nakus.sk ≠ nakup.sk, which prevent real invocation mistakes. It stops short of stating behavior when no price is found or how missing/ambiguous identifiers are resolved.

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 purpose and return fields, then usage and exclusions in a tight sequence; nearly every clause carries routing or output information. It is dense and slightly run-on, and the trailing 'Read-only, idempotent' clause is pure duplication of the annotations.

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 usefully enumerates the returned URLs and price units, and schema coverage fully documents the four optional parameters. For a multi-identifier lookup tool the only material gap is undefined behavior when the price is unavailable or identifiers conflict.

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 schema already explains q as a fallback substring, ean as preferred for scanned packs, answer as the Cite slug, and product as the catalog slug. The description restates the same identifier set without adding precedence rules or format details beyond the schema, so 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 (return) and resource (current landed unit price for one Slovak product Cite on nakus.sk), plus the concrete return fields buy_url, handoff_url, price_card_url. The unit-price scope and domain make it immediately distinguishable from search_cite_answers and get_price_card.

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?

Explicit trigger condition (user asks how much X costs per unit / cheapest shop) with the precondition that an answer slug, EAN, product slug, or clear q is already known. It names the fallback (call search_cite_answers first when slug/EAN unknown) and an explicit exclusion (PNG-only needs → get_price_card), so an agent can route correctly without inference.

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 readOnly, idempotent and closed-world, so the safety profile is covered. The description still adds real behavior beyond them: results are candidates only, no live pricing is returned, and the slug is the key to hand to the next tool. Pagination/ordering behavior is not mentioned, keeping it below a 5.

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?

Four short sentences, front-loaded with purpose, then the call-order rule, then the negative constraint. No filler, and the brand caveat is a single trailing clause.

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 still characterizes the return well enough for an agent: a list of candidate slugs, not live prices, and how to consume a slug downstream. Nothing needed to call this two-parameter read-only search 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%, so the schema already documents 'q' and 'limit' including the default 8 / max 20. The description's only extra signal is that a candidate's answer slug (or EAN) feeds get_unit_price's answer parameter; it adds nothing about search-text syntax or limit behavior.

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?

Names a specific verb and resource (search Slovak Cite Q&A slugs on nakus.sk) and adds concrete domain examples (diapers, laundry, pet food, coffee). It also explicitly distinguishes itself from the sibling tools by stating what it does NOT return (live €/unit).

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 ordering rule ('Use FIRST when you do not know the exact answer slug or EAN'), names the next tool to call ('get_unit_price with answer=<slug>') and routes card-only requests to get_price_card after a slug exists. When-to-use, when-not-to-use and alternatives are all covered.

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