Brandloupe Index

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

Annotations already declare readOnlyHint and closed-world scope. The description adds two useful behavioral facts beyond them: results are capped at 10 and only live stores are returned. However it says nothing about what happens when the cap is hit, whether/how to page past 10, or latency/rate limits — significant omissions for a search tool.

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 leads with the result cap and liveness constraint, then the filters, then the sort order. Info-dense with no filler, though the parenthetical enumeration makes it slightly long.

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 an 8-parameter, 0-required search tool with no output schema and no annotations covering result behavior, the description should say more about what a returned store record contains and how to go beyond the 10-result cap. It is adequate for invocation but incomplete for correct expectation-setting.

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 88%, so the schema already documents seven of eight parameters in detail (including the app/pixel key vocabularies). The description only echoes the filter names (category, country, apps run or lack, pixels, theme) without adding syntax, combination, or default-value 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?

States a specific verb+resource (find live Shopify stores), enumerates the filter dimensions, the result cap, and the sort dimensions. An agent can tell it is a filtered search, but it never names or contrasts the siblings (lookup_store, technology_usage), so the differentiation is only implicit.

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 filter enumeration — you reach for this when you want a cohort of stores matching criteria. There is no explicit when-to-use vs when-to-use-instead guidance relative to lookup_store (single store) or technology_usage (aggregate stats), which is the main gap.

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=true and openWorldHint=false, so safety is covered. The description adds genuinely non-obvious context beyond the annotations: the data comes from "the latest crawl" and therefore is snapshot/stale rather than live, and it enumerates the profile contents (traffic estimates, competitors, pixels) that would otherwise be hidden without an output schema.

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 with no filler, opening with the core purpose before enumerating payload fields. The long field list is dense but earns its place because no output schema exists to document the return shape.

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 one-parameter read-only lookup with no output schema, the description covers purpose, data provenance, and return contents adequately. Remaining gaps, such as behavior for an unknown domain and the implicit contrast with find_stores, are minor but real.

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% for the single domain parameter, including an example format (gymshark.com), so the schema carries the parameter burden. The description adds no additional syntax, normalization, or error semantics for the domain, which is the baseline-3 case.

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-equivalent (look up) and resource (one Shopify store's profile), and enumerates the returned fields, so the agent knows exactly what comes back. It does not differentiate itself from siblings like find_stores or technology_usage, which is the only thing keeping it from 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?

The phrase "One Shopify store's profile" implies a single-store lookup as opposed to the plural find_stores search, which is weak implicit routing guidance. There is no explicit when-to-use, when-not-to-use, or named alternative, so the agent must infer the split from the sibling names.

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=true and openWorldHint=false, so the safety profile is covered. The description adds useful scope context ('live' Shopify stores, aggregate breakdowns), but says nothing about data freshness, whether the result is a fixed report or paginated, or behavior on an invalid slug — so it only modestly exceeds what the annotations provide.

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 front-loaded with the most important information: the first states what the tool reports, the second supplies the input format. Long enumeration in sentence one is justified because there is no output schema to carry it, and there is no 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 correctly spells out the return dimensions, and it fully covers the one input parameter. Remaining gaps are minor but real: nothing on data recency, no mention of limits on returned lists (top countries / most visited stores), and no error behavior for malformed slugs.

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%, so the description carries the full burden for the single required slug parameter and does so well: it gives the exact construction rule for all three case types — app key with hyphens (judge-me), theme name + '-theme' (dawn-theme), pixel key (meta). That is concrete, actionable format guidance the schema does not supply.

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 concrete verb (counts/reports usage) plus the resource (live Shopify stores running an app, theme, or pixel) and even enumerates the specific outputs — category share, top countries, co-used apps, top stores. This makes it unmistakably distinct from find_stores, lookup_store, and weekly_changes, which are store-level or diff-oriented rather than technology-penetration analytics.

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 slug conventions signal that this tool is for app/theme/pixel level aggregate questions, but no alternative is named and there is no when-to-use/when-not statement relative to the sibling tools. Adequate but leaves the agent to infer the boundary.

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=true and openWorldHint=false, so safety is covered. The description adds meaningful behavioral context beyond that: the data is a snapshot comparison against the previous crawl, and it defines the thresholds used (e.g. price drops of 10% or more), which helps the agent interpret results. It does not cover pagination or result limits, keeping it short of a 5.

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, front-loaded with the core comparison and then the filter clause; the enumeration of change types is dense but earns its place by telling the agent what will be returned. No 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?

For a read-only, no-output-schema tool with fully documented optional params, the description covers what the tool aggregates and the comparison window. Minor gaps remain (whether country and category can be combined, response shape), but nothing essential 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 description coverage is 100%, so the baseline is 3. The description restates that filters are optional and scoped to one category or country, but adds no format or combination semantics beyond what the schema already documents.

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 ('Totals and examples from the latest weekly crawl compared with the previous one') and enumerates the change types covered (product launches, price drops, discounts, best-seller climbs, app store additions). This is clearly distinguishable from the store-lookup siblings (find_stores, lookup_store, technology_usage).

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 'Optionally for one category or country' clause implies scoping usage, but there is no explicit when-to-use guidance, no comparison against sibling tools, and no note on when the weekly snapshot is or isn't appropriate. Usage is only implied.

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