GoBuy Product Trust

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

Annotations cover the operation profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false), and the description adds substantial beyond them: the paid Bright Data collection trigger, the seven-day cache write, force_refresh's cost implication, pending-job resumption, sample-sorting caveats, the no-cookie sampling method, and the heuristic-authenticity caveat. This is exactly the extra context 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?

Front-loads verb, scope, and runtime before the routing and cost details. Every clause is load-bearing: cost, cache, latency, resumption, and the heuristic caveat each change how an agent should call or interpret the tool.

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 should hint at what comes back. It discloses sample ordering and the authenticity caveat, which is good, but never says what the analysis output contains (themes, sentiment, counts). Otherwise the operational picture is complete.

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%, so the baseline is 3. The description still adds operational meaning for force_refresh beyond the schema wording — that a later explicit call without it resumes a pending job with no new scrape — which is genuinely useful decision context for the caller.

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 + scope ('Analyzes up to 100 recent reviews') with a latency envelope, and explicitly distinguishes itself from siblings check_product_trust and compare_products. An agent can route to it without opening any 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?

Gives an explicit gating condition ('Use only when Amazon review-sample analysis is explicitly requested') plus named alternatives and what each alternative is for (trust score vs. ranking). When-to-use and when-not-to-use are both covered.

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 carry readOnly/idempotent/openWorld/destructive=false, so the 'read-only — does not modify any state or place orders' line is largely redundant. The description does add non-obvious behavioral context: the score>=55 PASS / 35-54 FLAG / <35 BLOCK gate semantics, the caveat that the verdict is an evidence tier rather than a GPV-1 checkout decision, and the disclaimer about marketplace records vs. product quality.

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 and the scoring rule early, then routing guidance, then caveats. Mostly every sentence earns its place, though the explicit read-only restatement duplicates the annotations and the quality-disclaimer sentence is somewhat padded.

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 it does: score range, full signal breakdown, and verdict tier are all described. Combined with the threshold semantics and scope caveats, an agent has everything needed to call and interpret this tool.

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?

With 100% schema coverage on only 2 params, the schema already documents both `retailer` (with enum) and `product_id` including an ASIN example. The description names the four marketplaces but adds no syntax or format detail 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 and resource ('Return the GoBuy Evidence Score (0-100) and complete signal breakdown for a single retailer listing') and scopes it to four named marketplaces. It actively distinguishes itself from siblings by naming `compare_products` and `analyze_reviews`.

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 when-to-use ('individual product lookups') plus two named alternatives with the selecting condition for each (multi-product ranking -> compare_products; requested Amazon review samples -> analyze_reviews). It even states what this tool never does (fetches reviews).

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 readOnlyHint, idempotentHint, non-destructive, and openWorld. The description adds real behavioral context beyond them: it only returns previously computed results and 'does not crawl', which tells the agent there are no side effects or fresh network fetches and implies a cache/not-found outcome. It stops short of describing the not-found response or freshness semantics.

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, front-loaded with what is retrieved and what it contains, then routing guidance. No filler or restatement of the title.

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, but the description enumerates the score dimensions the caller receives, and annotations carry the safety profile. It lacks return-shape or freshness detail, which is a minor gap for a low-complexity single-parameter read tool.

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 0% for the single 'domain' parameter, so the description's 'by domain' is the only semantic hint and it adds nothing about format (no scheme, lowercase, FQDN) beyond what the pattern enforces. With one parameter and a self-enforcing regex, this is adequate but not additive.

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 (retrieve) plus resource (previously scored store score) and enumerates the scored dimensions (agent-readiness, trust signals, structured data, review system). It explicitly differentiates from siblings scan_store and check_product_trust, so an agent can select it without opening another 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?

Gives explicit routing: 'Use this first for an existing store score', names scan_store as the alternative when the store is not yet scored, and names check_product_trust for product listings rather than storefronts. 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.

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

Adds genuinely non-annotated behavior: 'never fetches reviews', 'Unindexed products rank last', and 'This is not purchase advice'. The read-only/no-orders statement partly repeats readOnlyHint and destructiveHint=false, but the ranking and scope disclosures go beyond the annotation set.

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-loads the core action and scope, then layers usage routing, safety, edge behavior, and disclaimer in tight sentences with zero filler. 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?

With no output schema, the description must explain results; it covers ranking order, the unindexed-last edge case, and read-only scope, which is enough to call it correctly. It stops short of describing the response payload shape, a minor gap for a tool with no output schema.

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 retailer enum and product_id formats are already documented. The description only echoes the '2-20' array bounds already encoded in minItems/maxItems, adding no new semantic detail; 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 specific verbs (fetch Evidence Scores, rank) and the resource (2-20 retailer listings) ranked by GoBuy Evidence Score. It explicitly distinguishes itself from the sibling `check_product_trust` for single lookups, so an agent can separate the two without opening schemas.

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?

Names the triggering condition ('choosing between multiple products') and the explicit alternative for the adjacent case ('For a single product lookup, use `check_product_trust` instead'). The 'never fetches reviews' clause also implicitly routes review-analysis intent to the `analyze_reviews` sibling.

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 readOnlyHint=false, openWorldHint=true, idempotentHint=false, so the mutating/non-idempotent profile is partly covered. The description still adds real value: expected latency (~20s), that it updates the stored score, and that repeated calls can trigger new scans — side-effect and cost context not derivable from the hints alone.

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?

Dense but front-loaded: purpose first, then routing, then requirement/side effects, then docs link. Every sentence earns its place, though 'repeated calls can trigger new scans' partially restates the non-idempotent implication already given.

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, and the description conveys the gist of the result (a store score) plus latency and the fact that a stored score is updated. It does not describe the score's shape or range, but nothing essential for correct 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 0% for the single url parameter, so the description must carry it, and it does: 'requires a full HTTP(S) URL', which clarifies scheme/format beyond the bare 'string/uri' schema. It stops short of stating length limits or validation failure 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?

States a specific verb+resource (score a store) with the defining trait 'live with a fresh crawl (~20 seconds)', which immediately separates it from the cached sibling check_store_score. An agent can classify it 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?

Explicit trigger conditions ('when check_store_score returns 404 or a fresh scan is explicitly requested'), an explicit alternative to use otherwise ('check_store_score ... to retrieve an existing result without crawling'), and a routing note to check_product_trust for a different evidence type. This is textbook when/when-not/alternatives.

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