CUBBY HOUSE — AU Mattress Commerce for Agents

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

No annotations are provided, so the description carries the full behavioral burden. It discloses freshness ('Live', 'recent window') and the shape of the returned metrics, but says nothing about auth requirements, rate limits, or how the 'limit' interacts with results. This is partial disclosure for an annotation-free 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?

Two tightly written sentences, with the data content front-loaded and the usage guidance second. 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?

For a simple single-param read tool with no output schema and no annotations, the description conveys the metric content adequately. However, the lone parameter is left unexplained and there is no note on result ordering or default window length, leaving an agent to guess at invocation semantics.

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% and there is one parameter ('limit', maximum 20). The description never mentions 'limit', what it bounds, or how many retailers are returned by default. With low coverage, the description should compensate, and it does not.

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 concrete resource and its contents: 'catalogue size per retailer plus outbound click volume in the recent window.' That is specific enough to distinguish it from sibling tools dealing with profiles, products, and leads. It stops short of an explicit 'this is the retrieval verb for X' framing, so it lands at 4 rather than 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?

'Use to weight which retailers to surface first' supplies a clear decision context for calling the tool. It does not name alternatives or when-not-to-use conditions, which keeps it below 5.

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. It usefully discloses the return shape (ranked matches, confidence, reasons, affiliate_url), which is real added value, but it says nothing about auth requirements, rate limits, whether results are personalized/cached, or how ties are broken.

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?

Purpose is front-loaded in one sentence, followed by a dense but scannable parameter and return summary. The 'Params:' list is terse and every token carries information, though the terse dump style borders on schema restatement.

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 tool with no annotations and no output schema, the description supplies the key missing pieces: parameter value domains and the returned fields. It falls short only on default values, pagination/limit behavior, and the absence of any sibling-routing guidance.

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% and there are no enums in the schema, so the description must compensate — and it largely does, naming all 8 parameters and supplying value vocabularies (side|back|stomach|combination, pain point examples, AUD budgets, 1-10 firmness, bool|1-5 cooling). It omits defaults and the meaning/upper bound of limit, which the schema alone carries.

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 uses a specific verb and resource: 'Match a structured sleep profile to ranked products,' which is far more informative than the bare tool name. It does not, however, explicitly contrast itself with dome_search_products, so the agent must infer that this is profile-driven matching versus keyword search.

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 input shape — supply a sleep profile when you want ranked product matches — but the description never states when to prefer this over dome_search_products or dome_get_retailer_traction. No exclusions or prerequisites 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?

No annotations exist, so the description carries the full behavioral burden, and it discloses almost nothing: no auth requirements, no default sort, no description of whether 'q' is fuzzy or exact, no return shape, and no pagination semantics beyond the raw limit/offset names. The catalogue size count is the only real behavioral signal, which is thin for a 10-parameter 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?

Two tight sentences, front-loaded with the resource and scope before the parameter inventory. The param list mildly restates schema names, but the brief hints on q and sort give it some justification and nothing is 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?

For a 10-parameter tool with no annotations, no output schema, and 0% schema coverage, the description is too skeletal: it omits default ordering, the firmness scale, pagination expectations, and what a result record contains. An agent could invoke it but would be guessing on several inputs.

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 must compensate, and it only partially does: it clarifies that q is a keyword and enumerates the sort values (already in the schema enum), but min_price/max_price, firmness_min/max (what scale?), retailer, and limit/offset defaults are left entirely undefined. The names are largely self-explanatory, keeping this at a middling 3 rather than lower.

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 ('Search') and a precisely scoped resource ('CUBBY HOUSE Australian mattress catalogue'), even quantifying the scope (14 retailers, 145 products). The sibling tools (retailer traction, profile matching, lead submission) are functionally distinct, so an agent can route here without ambiguity.

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 by the word 'Search' plus the filter list; there is no explicit when-to-use statement, no exclusions, and no mention of when to prefer this over dome_match_profile, which could plausibly also surface products. Adequate but leaves the agent to infer routing.

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 behavioral burden, and it does disclose useful side effects – stored in Firestore, ops-notified, exportable by the operator. However it omits auth requirements, duplicate/idempotency handling, validation rules, and failure 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?

Two sentences, front-loaded with the core action and then a compact param list. The parenthetical list is slightly dense but nothing 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 no-annotation, no-output-schema mutation tool with six params at 0% schema coverage, the description is only partially sufficient – it names the params and side effects but lacks validation, dedup, and outcome details an agent would need.

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 must compensate; it enumerates all six params and flags product_id and ref_tag as optional and clarifies agent_id as 'your agent identity'. It does not give format or meaning for email/message/ref_tag, leaving real gaps.

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 ('Submit a qualified shopper lead into the CUBBY HOUSE pipeline') with scoping detail. It is clearly distinct from siblings like dome_search_products or dome_match_profile, though it does not explicitly name alternatives.

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 word 'qualified' hints at a gate but never defines it, and there is no when-to-use vs when-not guidance or any routing to/away from sibling tools. Usage must be inferred.

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