Invisible Doors — hidden doors & glass partitions

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

No annotations are provided, so the description carries full behavioral burden. It usefully discloses return content ('с ценой и файлами') and the catalog size, but omits whether the operation is read-only, authentication needs, 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?

Two tightly written sentences with zero waste. The catalog size and filter list are front-loaded, followed immediately by the alternative for custom sizes.

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 search tool with no output schema and no annotations, the description conveys return content (price and files) and routing to the correct sibling. Minor gaps remain around pagination defaults and what the 'files' entail, but the agent has enough to invoke correctly.

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 83%, so the schema already documents most parameters. The description lists filter categories (system, profile color, glass, max price) that map to existing schema descriptions, adding confirmation but no new syntax or format meaning.

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: selection from 318 ready-made partition configurations. It explicitly distinguishes from the sibling tool quote_partition for custom sizes, so an agent can tell them apart 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?

It gives explicit when-to-use context (ready-made configurations with filters) and names the alternative quote_partition for custom dimensions. The routing condition is unambiguous.

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 provided, so the description carries the full behavioral burden. It says nothing about read-only nature, return format, pagination, or size of the catalog, despite being the only source of such context. A lookup tool with a bare 1-param enum needs more disclosure than this.

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 purpose is front-loaded, which is good, but the single sentence is bloated with an exhaustive list of code prefixes (woodstock-, wpc-, egger-, hpl-, tile-, mirror0-3, glass-) that is heavy for a selection-time description and dilutes the core statement.

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, so the description is the only place return content could be characterized. It names content categories but gives no format, structure, or size expectations. For a single-enum lookup tool this is minimally sufficient but not 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 description coverage is 0%, so the description must compensate for the undocumented 'kind' enum. It partially does by splitting content by branch ('отделки дверей…' vs 'для перегородок — …'), mapping loosely onto the doors/partitions values, but never explicitly states that 'kind' selects which set is returned.

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 ('Справочник кодов' — a code reference) and enumerates the domains it covers (door finishes, RAL, edges, partition families, glass). An agent can tell this is a lookup tool distinct from list_door_models or quote_door. It does not explicitly differentiate from siblings, but the purpose is unambiguous.

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 tying the catalog to quote_door and quote_partition, which hints these codes are needed during quoting. There is no explicit when-to-use, when-not-to-use, or named alternative. Adequate but leaves the agent to infer the 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?

No annotations are provided, so the description carries the full burden. It usefully discloses the scope of information returned (contacts, showrooms, lead times, designer/architect terms), but says nothing about the form of the response or that it is a static, side-effect-free lookup. For a zero-parameter tool the burden is small, so a 3 is appropriate.

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 listing the covered topics with no filler. Efficient, though the topic list is dense and could be marginally better structured.

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, no-output-schema informational tool, the description adequately conveys what the agent will get. It could be slightly more complete by noting the response format or that no arguments are accepted.

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 no parameters, so there are no semantics to document. The baseline of 4 applies; the description neither adds nor detracts on this dimension.

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 informational purpose (how to order) and enumerates the content it covers: sales contacts, showrooms, production times, and conditions for designers/architects. This distinguishes it reasonably well from the sibling quote/list tools, though it never explicitly frames itself as the non-transactional information counterpart to `quote_door`/`quote_partition`.

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 can infer it should call this when a user asks about ordering logistics rather than requesting a quote or model list. No explicit when-to-use trigger, prerequisites, or named alternatives 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 burden, and it does disclose the return payload in useful detail (codes, finish groups, opening directions, size ranges, reference price for 800x2000, product-card links, 3D files). However, it says nothing about read-only nature being explicit, pagination, or how large the list is, leaving meaningful behavioral gaps for a no-annotation 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 dense sentence with no filler, and the core purpose is front-loaded before the enumeration of returned fields. The content list is long but each item earns its place by telling the agent what comes back.

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 describe the return shape, and it does so with a concrete field list including the reference price basis (800x2000). Combined with the zero-parameter schema, an agent has enough to call and interpret the tool, though usage context is thin.

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 schema has zero parameters, so there is nothing to disambiguate; the baseline for a parameterless tool is 4. The description correctly implies no filtering input is accepted (an unfiltered full list).

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 clear verb+resource ("Список моделей скрытых дверей") and scopes it to the Invisible Doors aluminum-frame line, so an agent knows exactly what entity is listed. It also previews the returned fields. It does not explicitly name a sibling it differs from, 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?

No when-to-use guidance, no prerequisites, and no mention of alternatives such as find_partitions, get_codes, or quote_door. The agent must infer that this is the catalog-lookup entry point versus the quoting tools from the name alone.

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 reasonably well: it discloses the return payload (price.rub as retail price, 'applied' = what was actually assembled, ZIP/GLB links), and notes a 20-30 s assembly time for non-standard configs. It stops short of stating permission/auth requirements or failure modes.

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, then returns, then timing, then a sibling pointer. Dense and largely waste-free, though the model-format enumeration (GLB, FBX, OBJ, DAE, IFC4, DXF) is verbose for a description.

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 must describe returns, which it does concretely (price.rub, applied, download links). Combined with the timing note and codes pointer, an agent has enough to invoke it, though 11 params at 55% coverage leave some gaps 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?

Schema coverage is 55%, so the schema already documents several params (color, model, finish, opening, backMaterial). The description adds only marginal semantic value, mainly hinting that two-sided finishes are supported, which maps loosely to the backColor/backFinish/backMaterial trio without explaining them.

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: it returns the price and a 3D model of a hidden door ('скрытой двери') parameterized by size and finish. The resource is specific enough to distinguish it from the partition-quoting sibling, though it never names that sibling explicitly.

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 (quote a door given size/finish) but there is no explicit when-to-use or when-not-to-use guidance. The only routing hint is the trailing 'Коды — get_codes(kind=doors)', which points to a sibling for obtaining model/finish codes rather than stating which quote tool to pick.

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 it does disclose the return payload in unusual detail: an evaluation containing price, status and on-site items to confirm, plus ZIP archives in GLB/FBX/OBJ/DAE/IFC4/DXF/SVG, a GLB link, and a configurator link. It omits side effects, permissions, or cost/latency traits, but for what is effectively a read/compute quote tool this is solid disclosure.

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 core purpose is front-loaded in the first clause, and every following fragment adds a distinct piece of information (what it accepts, what it returns, where to get codes). It is dense and slightly run-on but wastes little.

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 quote tool with no output schema, the description compensates by enumerating the returned evaluation fields and artifact links. Combined with the required-vs-optional split the agent has enough to call it correctly; only the sibling-choice criteria remain implicit.

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 75%, so the schema already documents most parameters (family, finishId, infillId, schemeId, leafDesignId, finishColorCode). The description restates those concepts as a shopping list (схема открывания, профиль, стекло, рисунок) without adding syntax or format detail beyond what the schema provides, so baseline 3 is 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?

States a specific verb+resource (цена/3D-модель перегородки) and the exact scope: glass LOFT or door-leaf partitions sized to an opening. It also distinguishes itself from the sibling quote_door by naming the partition families it handles and routes code lookups to get_codes.

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 points to get_codes(kind=partitions) for the code sub-need, which is a useful routing hint, but never states when to choose this tool over quote_door, find_partitions, or how_to_order. Usage is implied by the purpose rather than explicitly bounded.

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