Comparr

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

Annotations already establish this as a safe read (readOnlyHint=true, openWorldHint=false), so the description is free to add the operationally important context: the freshness window (checked within 48h), the reference period (previous 90 days lows), the multi-reading requirement, and the new-condition/Amazon-only scope. That is meaningful beyond the annotations, though it says nothing about result volume or rate limits.

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 concept, and every clause in the first sentence carries a qualifying criterion an agent would otherwise have to guess. The first sentence is dense and clause-heavy, but nothing is padding; the two follow-up sentences on return payload and filtering are short and useful.

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 states what each deal returns (reference price, period, number of reading days), and it covers qualification criteria and filtering. Only edge details such as ordering, pagination or behavior when fewer deals exist than 'limit' are left 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 both parameters are already documented; the description only restates the *optional* nature of the name filter and adds an example-free gloss ('words in the product name'), while never mentioning 'limit'. This meets the baseline of 3 without adding real semantics 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?

The description states a specific resource ('Current verified price drops') and goes further by defining exactly what makes a drop qualify (same offer below its own 90-day low, multiple reading days, checked within 48h, new condition, Amazon re-verified). This clearly distinguishes it from get_price_history or search_products, though it never names those siblings 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 rather than stated: an agent can infer this is the tool for pre-computed deal listings and that 'query' narrows by product name. There is no explicit when-to-use versus get_price_history or search_products, and no stated exclusions, so the agent must infer routing from the resource name alone.

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 safety (readOnlyHint=true, openWorldHint=false), so the bar is lower, and the description adds genuinely non-obvious behavior: readings are periodic snapshots (often weekly), not daily tracking, plus an instruction to quote dates and reading counts. This data-freshness caveat is exactly the kind of disclosure annotations cannot carry.

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, zero filler, with the returned data shape front-loaded and the snapshot caveat plus quoting instruction following. Every clause carries information an agent needs.

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 returns and does so adequately: best-price-per-day series plus per-offer series. Combined with the snapshot cadence and window parameter, an agent has enough to call the tool and interpret results 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% and both parameters (product, days with default 180 and 1-365 range) are documented in the schema itself. The description adds only the notion of 'readings' sparsity, which indirectly frames the days window, but specifies no format for the product identifier beyond what the schema says.

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 ('recorded price history of one product') and clarifies the two granularities returned: best price per day across all offers and the per-offer series. It implicitly separates itself from get_product (current state) and get_deals, but never names a sibling to make the distinction explicit.

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?

Useful context is implied via the stated goal ('so you can tell a real price drop from a cheaper seller appearing'), which tells the agent this is the tool for price-trend questions. However, there is no explicit when-to-use/when-not guidance and no alternative tool is named or excluded.

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 the safety profile (readOnlyHint=true, openWorldHint=false), so the description's value is in disclosing the payload: price-check dates, exact seller, condition, and a computed buy-timing verdict. That is meaningful behavioral context, especially since there is no output schema. It omits error behavior for unknown slugs and any freshness/latency caveats.

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 identifies the resource first, then enumerates the returned fields, all of which matter because there is no output schema. No filler or redundancy.

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 one required parameter and no output schema, the description carries the burden of describing returns, and it does so with a concrete field list and the verdict's provenance ('computed from Comparr's recorded price history'). Minor gaps remain around error cases and result ordering/pagination.

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 the schema only says 'Product id or slug.' The description adds provenance for that value (obtained from search_products or get_deals), which is genuine meaning beyond the schema. Baseline would be 3; the sourcing hint lifts 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 and resource ('All current offers for one product') plus the scope of the result set, which distinguishes it from the multi-item siblings get_deals and search_products. Sibling differentiation is implicit rather than explicit, but an agent can tell this is the single-product detail lookup.

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 tells the agent where the product id/slug comes from (search_products or get_deals), which is useful upstream routing, but it never says when to prefer get_deals or get_price_history over this tool. Usage is implied by the resource scope rather than stated.

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 substantive behavior beyond the annotations: the tool may initiate a new comparison (a side effect consistent with readOnlyHint=false), the result includes every offer, exact seller, item condition, and price-check date, and there is a pending/polling lifecycle. It stops short of stating auth requirements or rate limits, but covers the non-obvious traits.

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 sentences, front-loaded with the core action, then return contents, then the pending case. No filler and every sentence 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?

No output schema exists, so the description carries the return-value burden and does so (ranked products, offers, seller, condition, check date), plus the asynchronous pending flow. An agent has enough to call correctly and interpret the result.

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 with examples and defaults. The description adds only indirect meaning ('in their own words', market currency tie-in via the country sites) and no syntax or format detail 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 ('Compare the prices of a product category or a specific model across merchants') and names the two regional sites. An agent can distinguish this from get_product, get_deals, and get_price_history without opening a 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 explains the asynchronous case: if no comparison exists, one is started, status is 'pending', and the agent should re-call with the same query after ~60 seconds. That is real when-to-use guidance, but it never contrasts this tool against its siblings (get_deals, get_price_history, get_product).

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