PriceDash

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so safety is covered; the description still adds real behavior not in the schema: results are live, deduplicated to one offer per shop, and capped at five. It stops short of saying whether the cap is global or per shop/category combination.

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?

One sentence, front-loaded with what the tool returns, with zero filler. The colon list is slightly compressed but every clause maps to a real capability.

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-shape explanation is unnecessary, and the description covers scope, dedup and result cap. However, for a low-complexity tool with a sibling it omits the one thing structured fields cannot supply: why an agent would pick this over search-vouchers.

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 enum meanings and the fact that filter is ignored when category is supplied, so the schema carries the semantics. The description merely restates the same modes and category concept without adding format, precedence, or default details beyond the 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+resource: browsing live offers/deals across UK shops, with the notable idempotency detail of 'one per shop, up to five'. It does not name or distinguish itself from the sibling search-vouchers, so an agent cannot tell the deals-vs-vouchers boundary from this text alone.

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?

There is no explicit when-to-use or when-not-to-use guidance, and the sole sibling (search-vouchers) is never mentioned or contrasted. The enumerated modes read as parameter documentation rather than selection guidance.

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 behaviour, so the description only needs to add context — and it does: a five-result cap, the fields returned per code (code, end date, last-checked date, PriceDash link) and the ordering rule that offers checked in the last 30 days rank first. It stops short of error behaviour for unmatched shops, but the ranking and cap are genuinely useful extra signal.

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?

One efficient sentence with the result shape and ordering rule front-loaded. The opening clause ('Live voucher codes and offers PriceDash lists for one UK shop or brand') is slightly tangled but nothing is redundant.

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 an output schema present and full parameter coverage, the description only needs to frame the call, which it does — result cap, ordering semantics and per-code fields. The only real gap is behaviour for a shop with no matching vouchers or a non-UK brand.

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?

There is a single parameter with 100% schema description coverage (the schema already gives examples like 'Currys', 'Boots', 'ASOS'). The description adds only the scope hint that it must be one UK shop or brand; it offers no extra format or ambiguity guidance beyond that, 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?

The description clearly identifies the resource: live voucher codes/offers for one UK shop or brand, capped at five results. The retrieval verb is only implicit (the description narrates what PriceDash 'lists' rather than saying 'search' or 'get'), and it never names the sibling browse-deals, so an agent can't fully distinguish the two from this text alone.

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?

Usage is only implied: 'for one UK shop or brand' tells the agent this is a per-brand lookup, which indirectly contrasts with a general deals browse. There is no explicit when-to-use statement, no mention of the browse-deals sibling, and no guidance on what happens for an unknown or non-UK brand.

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