Comparr

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

Annotations only cover the safety profile (readOnly, non-destructive, closed-world), but the description adds substantive behavior: the verification criteria that qualify a deal, the 48h re-check window, several days of readings required, new-condition-only and Amazon-only scoping, and that each result carries its proof (reference price, period, reading count). That is exactly the extra context 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?

Front-loaded with the core noun phrase and then compressed into a single dense sentence of qualifying criteria plus one sentence on returned proof and one on filtering. Nearly every clause carries selection-relevant meaning, though the criteria stack is heavy enough that a bulleted split would read faster.

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 compensates by naming what each deal returns (reference price, period, reading days) and by bounding the data's freshness and condition scope. Combined with a fully documented two-parameter schema and read-only annotations, an agent has everything it needs to call this correctly.

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 both limit and query are already documented with an example. The description only restates that filtering by words in the product name is optional, adding no syntax, matching rules, or default-value information beyond the schema. 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 resource ('current verified price drops') and defines it operationally: the SAME offer cheaper than its own 90-day lowest recorded price, backed by multiple reading days, re-checked within 48h, new condition, Amazon offers re-verified. That definition is unique against get_price_history (historical series) and search_products (general search), so an agent can route correctly even without the siblings being named.

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 implied rather than stated: 'Current verified price drops' tells the agent this is for spotting live bargains, and the query filter explains one narrowing option. However, it never says when to prefer this over get_price_history (e.g. to inspect the underlying readings) or search_products, and no exclusions or prerequisites are given.

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 establish the safe-read profile (readOnlyHint=true, destructiveHint=false, openWorldHint=false). The description adds genuinely new behavioral context: readings are periodic dated snapshots (often weekly) rather than daily tracking, and the dual series is explained as the way to tell a real drop from a cheaper seller appearing. It stops short of describing pagination or result shape.

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 tight sentences, front-loaded with what is returned and followed by the caveat that changes how the data should be read. Every clause carries information; nothing is redundant with the title or 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 must carry the return-value burden, and it does explain the two series and the snapshot cadence. Minor gaps remain (no mention of ordering, result shape, or behavior when the product has no history), but an agent has enough to call it correctly.

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% with only two parameters, both already documented (product id/slug, days window with default 180 and bounds). The description reinforces the single-product scope but adds no syntax, default, or format 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?

The description gives a specific resource and scope: 'Recorded price history of one product', and clarifies the two data series returned (best price per day and per-offer series). It distinguishes the tool from a current-deals tool by emphasizing recorded history, though it never names the siblings get_deals/get_product/search_products explicitly.

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 implied by the purpose statement – an agent can infer it is the tool for retrieving a single product's price timeline – but there is no explicit when-to-use, when-not-to-use, or routing against the sibling tools. The snapshot-cadence note adds interpretive context but is not a usage rule.

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 establish readOnlyHint=true, destructiveHint=false, so the safety profile is covered. The description adds substantive behavioral context beyond that: it discloses the returned fields, that prices are dated by when they were checked, and that the buy verdict is derived from Comparr's recorded price history.

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?

A single front-loaded sentence that opens with the core scope ('All current offers for one product') before detailing the payload. No filler, no repetition of the title, every clause carries 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?

With no output schema, the description carries the burden of describing the return payload and does so well. Minor gaps remain: no mention of what happens when no offers or no price history exist, and no note on currency or result ordering, but nothing critical for invocation 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% for the single 'product' parameter, so the schema already documents the id-or-slug format. The description only restates the identifier and hints at where to obtain it, adding no new syntax or constraint detail, 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 ('All current offers for one product') and then enumerates the payload an agent gets back (checked date, exact seller, condition, buy verdict). It also distinguishes itself from siblings by naming search_products and get_deals as the places the required id/slug comes from.

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?

The description gives the precondition for calling it (you need a product id or slug from search_products or get_deals), which is real routing guidance. It does not explicitly say when to prefer this over get_deals or get_price_history, so it falls short of full when/when-not coverage.

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?

Adds substantial context beyond annotations: it discloses the return payload shape (ranked products, every offer, seller, condition, price-check date) and, importantly, the asynchronous behavior — a missing comparison is started and returns status 'pending' with retry_after_seconds, resolvable ~60s later. This also explains why readOnlyHint is false despite the read-like framing.

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 core purpose, then layered with return detail and the pending/retry caveat. Information density is high with no filler, though the async clause is somewhat dense and could be tightened.

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 carries the full burden and does so well: it describes the returned fields, the merchant coverage, and the pending-status edge case with a retry hint. Nothing essential for a correct call 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 query, limit and max_price. The description mirrors the query concept (category or specific model) but adds no syntax, format or currency nuance beyond what the schema provides; baseline 3 is appropriate.

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 — compares product prices across merchants — with geographic scoping (comparr.fr / comparr.co) that clearly separates it from sibling lookups like get_product and get_price_history. An agent can identify its role 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?

The description conveys when the tool is useful (comparing a category or a specific model across merchants), but never explicitly names the alternatives (get_product, get_price_history, get_deals) or states when NOT to use it. Usage is implied rather than prescribed.

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