Drop Beacon

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add substance, and it does: it discloses the exact signals compared (current lowest in-stock price, 90-day low, all-time low, high, watch duration) and the return shape (verdict + confidence). The explicit 'summary only, not full price history' boundary is valuable behavioral context beyond the annotations.

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, both load-bearing: the first defines the computation and output, the second defines the scope boundary. Nothing is repeated from the title or annotations, and the core operation is front-loaded.

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 characterize the return value, and it does ('plain verdict with a confidence level', summary only). For a one-parameter, read-only tool this is nearly complete; only minor details such as behavior when a product name is ambiguous are unaddressed.

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 and the schema describes it at 100% coverage, including accepted formats (URL, slug, product name) and length limits. The description adds nothing about the product argument, so the baseline of 3 applies when the schema carries the full burden.

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 names a specific operation: comparing a product's lowest in-stock price against Drop Beacon's observed range (90-day low, all-time low, high, watch duration) and returning a verdict plus confidence. That is concrete enough for an agent to know exactly what the tool produces. It doesn't explicitly contrast itself with siblings like top_deals or find_offers, so it stops short of a 5.

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: you call it when you have one product and want a deal judgement. The clause 'Summary only; it does not return the full price history' is a useful negative constraint that steers an agent away from expecting history, but no alternative tool is named and no preconditions 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 cover the safe-read profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower, and the description still adds real context: prices are observations that can drift, the retailer page is authoritative at checkout, and ambiguous names produce an other_matches list. What it doesn't cover — result ordering, empty-result behavior, or freshness thresholds for 'last checked' — are minor gaps.

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 behavior and result payload, then ambiguity handling, then the staleness caveat. The first sentence is long and stacks many return fields, but nothing is redundant or 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?

With no output schema, the description carries the return-shape burden and does it well: it names the fields returned and explicitly handles the multi-match case. It stops short of stating what an empty result looks like or whether results are ranked by price, which an agent calling a price-comparison tool would want.

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 single parameter already documents URL/slug/name forms with examples, so the description need not repeat it. It adds only a light hint that name lookups are fuzzy and may resolve to several models, which is marginal value beyond the schema's own description.

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 the retailers that currently have it in stock' for one product, and enumerates what each result carries (price, configuration, last-checked, coupon, buy link). That is clearly distinguishable from search_products or top_deals, which operate over sets rather than a single product.

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 'For one product' — an agent can infer this is the per-product lookup path — but the description never names an alternative or states when not to use it (e.g. when the product is unknown, use search_products first). No prerequisites or exclusions 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 declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description adds real value by enumerating the returned fields, which matters because there is no output schema; it does not, however, say what happens when the brand is unknown or unmatched.

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 compact sentence with the resource stated first and the payload listed after; nothing is padded. It is a sentence fragment rather than a full clause, but that costs no clarity here.

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 tool with full annotation coverage, the description supplies the one thing structured fields do not: the shape of the return value. Only the not-found / no-match behavior is left unstated, which is a minor gap for this complexity.

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 single parameter already documents its type, length bounds, and an example ('Spyderco'), so the schema carries the burden. The description adds no matching semantics such as whether the name must be exact, a prefix, or fuzzy.

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 names the specific resource (a brand's Drop Beacon profile) and enumerates the fields returned: page link, website, maker/retailer classification, in-stock product count, and public discount code. The verb is only implied by the tool name ('get'), but the resource and payload are unambiguous enough that an agent can distinguish it from deal/offer/product siblings.

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 — the agent must infer that this is a per-brand lookup used when you already have a brand name, rather than a discovery tool. No alternatives are named and no exclusions given, despite siblings like search_products and find_offers that could plausibly overlap.

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, closed-world, non-destructive behavior, so the safety profile is covered. The description adds real context beyond that: what a result contains (brand, catalog price, page URL) and the non-obvious rule that models and configurations such as steel or color are separate products, which changes how the agent interprets hits. It does not cover result ordering or pagination behavior.

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 tight sentences: what it searches, what comes back, then the routing hint. The catalog scope and the separate-variants caveat are front-loaded before the pointer to find_offers, and no sentence is 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?

There is no output schema, and the description compensates by naming the returned fields (brand, catalog price, page) and the catalog-price-versus-live-price distinction. For a three-parameter search tool this is nearly complete, with only result ordering and empty-result behavior 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 coverage is 100%, with query, limit, and in_stock_only all documented in the schema itself, so the baseline is 3. The description adds only indirect guidance about query semantics (variants are separate products), and says nothing about limit or the default in-stock filter, so it does not meaningfully exceed 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 and resource ('Search Drop Beacon's catalog of 150,000+ everyday-carry products') and scopes it with concrete category examples (knives, flashlights, sliders, pens, multitools). It also separates itself from the price-oriented siblings by naming find_offers as the follow-up for live prices.

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 explicit sequencing guidance ('Use find_offers next for live prices across retailers'), which tells the agent this tool is the catalog lookup step, not the deal-hunting step. It does not state when not to use it versus deal_check, top_deals, or upcoming, but the context it does provide is clear.

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 only declare it as a safe, idempotent, closed-world read. The description goes well beyond that by disclosing the data freshness window (checked within 3 days), the exact discount threshold, and the contents of each result including the lowest recorded price used to sanity-check the was-price. That is substantive behavioral context an agent could not infer from the annotations.

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 scope and qualification rule front-loaded before the result-field inventory. The enumeration of result fields is dense but each item is informative and earns its place.

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 six-parameter filtered search tool with no output schema, the description covers scope, eligibility criteria, freshness, result shape, and available filters. Nothing an agent needs in order 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 coverage is 100%, and every parameter (sort, brand, limit, query, category, min_percent_off) is documented with defaults and enums in the schema itself. The description only adds that filtering is available by keyword, category or brand, which restates rather than extends the schema — baseline 3 is correct.

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 names a specific resource (live markdowns on EDC products Drop Beacon tracks) and states the exact inclusion rule: in-stock items at least 10% below the seller's own compare-at price, verified within the last 3 days. That is far more precise than the title and lets an agent distinguish it from siblings like deal_check and find_offers.

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 clear context for when this tool is appropriate — you want current, verified discounts rather than general offers or upcoming drops — and notes the filter axes (keyword, category, brand). It never explicitly says when NOT to use it or names a sibling (e.g. deal_check for a single product) as the alternative, so it stops short of full routing 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 cover read-only, idempotent, non-destructive, and closed-world behavior, so the bar is lower. The description adds meaningful context beyond that: the 7-day recency window, that giveaways are free to enter, and that draw dates and entry links are included.

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 sentence with no wasted wording, and the core 'what's new' framing is front-loaded before the qualifying details.

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 two-optional-parameter read tool with rich annotations and no output schema, the description is nearly complete. A minor gap is not clarifying that the limit and category filters apply only to new drops, not giveaways.

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 the limit and category parameters are fully documented in the schema. The description adds little parameter-level meaning beyond noting the 7-day recency window, making the baseline 3 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?

The description states a specific resource and scope: in-stock products Drop Beacon first saw in the last 7 days, plus live giveaways with draw dates and entry links. It is clear what the tool returns, but it does not explicitly distinguish itself from siblings like deal_check or top_deals.

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 'What's new in EDC right now,' giving a reasonable sense of when to call it. However, it never states when not to use it or points agents to alternatives such as top_deals or search_products.

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