Escrova

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

With no annotations, the description carries the full burden and discloses auth requirements ('No wallet and no signature'), caching behavior, quota cost for cold shelves, and the estimate caveat for counts via countScope. This is rich behavioral context beyond typical schema details.

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?

The description is front-loaded and nearly every sentence carries operational information, which is justified by the absence of an output schema. However, the long run-on output enumeration and semicolon-heavy clauses make it dense and harder to scan than ideal.

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 annotations and no output schema, the description supplies output fields, auth, cache/quota behavior, workflow chaining, and the count-estimate caveat. An agent has enough information to invoke this tool correctly and understand its operational costs.

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?

Both parameters are already fully documented in the schema. The description adds endpoint URL shapes and reinforces that nodeId targets a category under a department, but it does not add significant parameter-specific constraints or formats 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 verb/resource—read one shelf/category node—and enumerates the returned groups: children, childrenDeep, brands, facets, aspectTiles, siblings, related, and deals. The opening 'narrow towards a purchase without inventing keywords' and the 'rather than walking the tree' contrast make its scope distinct.

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 use context, directs chaining engineParam back to search_products and contentAt to compare_landed_cost, and warns against walking the whole tree. It does not explicitly state the prerequisite list_categories call or when to prefer siblings like get_deals or get_directory.

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?

With zero annotations the description carries the full burden and does so: no wallet or signature required, results come from cached rows so no catalogue call is spent, an unknown tab returns 400 rather than being guessed at, and each row exposes cachedAt as the timestamp of price validity. That covers auth, cost, error behavior, and freshness — well beyond the 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?

Front-loaded with the task framing and the endpoint, and nearly every sentence adds a distinct operational fact (auth, caching, 400 on bad tab, cachedAt handoff). The telegraphic phrasing ('A selection over rows this site has already cached') is slightly compressed and costs a beat of readability.

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, non-destructive read with no output schema and no annotations, the description covers invocation, auth, cost, failure mode, and the key returned field. It does not describe the shape of the returned deal rows beyond cachedAt, which leaves the agent guessing about other fields.

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 single tab parameter is already documented, but the description adds meaning by explaining that door:<slug> scopes to one department and by tying the slug source to list_categories. It still does not spell out expected slug format or what each named tab actually contains.

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 ('GET /api/agent/browse/deals?tab=<tab>') and frames the task it serves ('find something on offer'). The enumeration of tabs plus the note that results come from already-cached rows distinguishes it from catalogue-searching siblings like search_products and get_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 a clear trigger ('For a "find something on offer" task') and routes the agent elsewhere for the adjacent step: rank with compare_landed_cost before quoting, and pull the door slug from list_categories. It stops short of stating when this tool should NOT be used (e.g. live pricing versus cached rows), so no explicit exclusion is offered.

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?

With no annotations, the description carries the full burden and does so well: it discloses no wallet/signature requirement, that it is served entirely from cached rows at zero catalogue cost, and that unfetched pictures or counts return null rather than triggering a fetch. That null-on-stale behavior is a non-obvious trait an agent would otherwise misread as an error.

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 payload shape, then endpoint, then auth, then caching semantics, then the sibling routing rule — a sensible order with no dead sentences. The shop/shelf metaphor adds a little verbal overhead but does reinforce the 'one read vs. walking down' tradeoff.

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 zero-parameter read with no output schema, the description supplies the return shape (three nested levels), the freshness contract, the auth posture, and the alternative tool. There is essentially nothing else an agent needs before calling it.

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?

The tool takes zero parameters, so the baseline is 4; there is nothing for the description to disambiguate. The description's implicit point that no filtering arguments exist is consistent with the empty 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 exactly what comes back — departments, the groups under them, and the links under those — plus the endpoint (GET /api/agent/browse/directory). The closing sentence names the sibling tool it replaces (get_category), so an agent can distinguish it without inspecting either 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 selection rule: 'Prefer this over repeated get_category calls when you are still deciding where to look.' That names both the alternative and the condition that selects it, which is exactly the routing guidance an agent needs among the seven siblings.

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?

With no annotations supplied, the description carries the full burden, and it does disclose two useful behavioral facts: the underlying endpoint (GET /api/config/fees) and that no wallet or signature is required, so the agent knows this is an unauthenticated read. It does not describe the response shape, caching, or whether fees can change mid-session, which matters for a pricing tool with no 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?

Three short sentences, front-loaded with what is returned, then the purpose, then the endpoint and auth posture. Nothing is padded and no sentence restates the tool name.

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 zero-parameter config read with no annotations and no output schema, the description covers what is returned, why it is called, and the auth requirement. The one remaining gap is the shape of the returned fee/delivery-rate data, which the agent must discover at call time.

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?

The tool takes zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description correctly implies no inputs are needed by noting no wallet and no signature.

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 pair — 'the current fee schedule and delivery rates' — with an implied read verb, which is far more concrete than the title alone. It does not explicitly distinguish itself from the sibling get_prices, which an agent could plausibly confuse with fees, 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?

The clause 'so a total can be explained before anyone pays it' implies the moment of use (pre-payment total explanation), which is genuine but indirect guidance. There is no explicit when-not condition and no named alternative among get_prices, get_terms, or get_deals.

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?

With no annotations, the description carries the full burden and does disclose one important trait: no wallet and no signature are required, implying a public unauthenticated read. It also names the underlying GET endpoint, reinforcing read-only semantics. It omits staleness/refresh cadence, rate limits, and whether prices are cached, which matter for a 'live' price feed.

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 short sentences, front-loaded with what the tool returns, which is the right ordering. The raw endpoint path 'GET /api/prices' adds little for an agent and is the one sentence that doesn't fully earn 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 zero-parameter read tool this covers purpose, auth requirements, and a deployment caveat, which is nearly enough. However, with no output schema the description should say more about the return shape—e.g., whether it is a list of coin/price pairs and which coins are included—and it says nothing about how fresh 'current' prices are.

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?

The tool takes zero parameters, so there is nothing to disambiguate; baseline is 4. The description correctly implies no filtering or symbol selection is possible and that the result set is fixed to the coins shown on Escrova.

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: current USD prices of coins shown on Escrova. An agent can immediately tell this is a price lookup rather than anything covered by the sibling tools (categories, deals, fees, terms, products). It doesn't explicitly name a sibling it is not, so it falls just 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 only implied: an agent infers it should call this to see current coin prices, and the note that checkout takes USDC only hints at why prices matter. There is no explicit when-to-use, when-not-to-use, or named alternative among the siblings.

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?

With no annotations, the description carries the behavioral burden and does well: it discloses that the values are read server-side, never taken from the request, and that no wallet or signature is required. It does not cover error behavior or rate limits, but the core safety and auth profile is clear.

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-load the return values, then explain the relationship to accept_terms and the auth posture. The endpoint reference is compact and no sentence is wasted.

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 simple zero-parameter read tool with no output schema, the description explains what is returned, where the values come from, and how they relate to accept_terms. 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?

The tool has zero parameters, so the baseline is 4. The description correctly adds no parameter meaning because there are none to explain.

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 verb and resource: it returns the current Terms of Service and Privacy Policy version plus document hash. It also names the related accept_terms tool, making its role distinct from a generic fetch.

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 clearly implies when to use it: to obtain the exact values that accept_terms will record. It does not give explicit when-not guidance or name alternative tools, but the context is sufficiently clear for a zero-parameter read tool.

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?

With no annotations provided, the description carries the full behavioral burden and does so well: it identifies the GET endpoint, says no wallet or signature is needed, notes cache serving, and warns that a cold department picture costs a catalogue-quota call shared with shoppers. Those are meaningful operational details beyond what a bare schema would reveal.

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?

The description is front-loaded with the main instruction and remains reasonably tight. Some phrasing is more colorful than necessary, but the sentences still convey useful routing, endpoint, auth, cache, and quota 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?

For a parameterless, annotation-free tool with no output schema, the description supplies the essentials: what is returned, how the returned slugs are used, the endpoint, authentication expectations, cache behavior, and quota implications. Nothing critical for correct invocation appears to be 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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter syntax that needs explanation. The description appropriately focuses on output routing instead, mentioning the slug that get_category later consumes.

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 outcome: it returns the sixteen departments, each with the slug consumed by get_category and a picture. It also explicitly distinguishes this entry point from keyword search and from get_category, so an agent can identify the tool's role 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?

It gives clear routing guidance: start a shopping task here rather than guessing search words, then use get_category on a department to get brands, filters, and listings. This names both the alternative and the follow-up tool, making the when-to-use condition explicit.

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?

No annotations are supplied, so the description carries the full burden, and it does substantial work: it declares no wallet and no signature are needed (auth/prerequisite), warns that a search "spends a paid provider call" (cost), and notes that REST pagination and degraded-source metadata come back unchanged. What it omits is the shape of the result items themselves, which matters with no 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?

Front-loaded with the core action and the source list, then proceeds to prerequisites, filter wiring, and alternatives in a sensible order. It is dense and jargon-heavy ("engineParam", "shoprs", "ebayAspectFilter") and the raw endpoint line adds little, but no sentence is truly wasted.

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 15-parameter, zero-annotation, no-output-schema tool the description covers the highest-risk items well: auth, cost, filter provenance, and pagination passthrough. It remains incomplete on return-value structure and on roughly half the parameters, which an agent would have to infer from names alone.

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?

Coverage is only 27% across 15 parameters, so the description must compensate, and it partially does: it explains that a brands[].engineParam from get_category belongs in engineParam (sent as the eBay aspect filter) and that shoprs holds a Google filter option. However, sort, limit, page, the price/rating filters, freeShipping, and the three ebay* parameters get no semantic treatment, leaving most of the surface to name inference.

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 products across the marketplaces") and enumerates the exact searchable sources plus the "all" option, so the agent knows the reach of the call. The closing sentence distinguishes it from list_categories/get_category, which narrow rather than guess.

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 says when to prefer the alternatives: "when you know roughly what department a thing is in, list_categories and get_category narrow further for less." It also flags the cost of using this tool versus those. It does not address other siblings like get_deals or get_prices, so it stops short of a full routing matrix.

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