htmlkin

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

With no annotations, the description carries the full burden, and it discloses key behaviors: the deletion is irreversible, the site stops opening at its address, and a custom domain remains in the account while its association is removed. It does not cover error cases or permissions, but the most important side effects are transparent.

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: the first communicates the core destructive action and result, the second handles the important domain edge case. No filler or repetition.

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 single-parameter tool with no output schema, the description covers the essential context: permanence, effect on the site's URL, and the domain exception. It is sufficiently complete for correct invocation, though it could mention what the agent should expect in response.

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%, and the schema already explains that page_id is the site identifier from htmlkin_publish. The description only restates 'по идентификатору', adding little beyond the structured parameter definition.

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 clearly states a specific action ('Безвозвратно удаляет ранее опубликованный сайт') with the resource and effect. It also distinguishes itself from siblings like htmlkin_publish and htmlkin_update by emphasizing deletion and irreversibility.

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 use case is clear: use this when a previously published site must be permanently removed. It does not explicitly mention alternatives or when not to use it, but the deletion purpose is distinct enough from the sibling tools that no ambiguity remains.

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 discloses what is returned (metadata fields) and implies a read-only operation. However, it omits error behavior (e.g., what happens if the site is not found) and does not explicitly state that no changes are made, which would be useful given the absence of readOnlyHint.

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 a single, efficient sentence that leads with the action and immediately lists the returned data. Every word earns its place with 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 one-parameter read tool without an output schema, the description adequately lists the return fields and resource state. It lacks details on error handling and does not explicitly confirm the operation is non-mutating, but these are minor gaps for a metadata getter. Overall it is sufficiently complete for correct invocation.

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 baseline is 3. The description adds meaningful context beyond the schema's generic 'Идентификатор сайта' (site identifier) by specifying the site must be previously published and enumerating the metadata tied to that identifier. This helps the agent understand the required state of the resource.

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 the specific verb 'Возвращает метаданные' (returns metadata) with a clear resource: previously published site. It enumerates the exact metadata fields, making the tool's function unmistakable. It clearly distinguishes from sibling tools (delete, publish, update) as the read-only metadata retrieval operation.

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 description clarifies the tool operates on 'ранее опубликованного сайта' (previously published site), implying it should be used after publishing and not for unpublished resources. However, it does not explicitly mention alternatives or state when not to use this tool, so it falls short of a 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?

No annotations are provided, so the description carries the behavioral burden. It discloses the outcome (returns public URL), the exclusivity constraint, and the binary-asset fallback. It does not mention idempotency, whether an existing subdomain is treated as an error (only in schema), or authentication expectations, leaving some behavior implicit.

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?

Four short sentences, front-loaded with purpose and return value; each sentence adds a constraint or routing hint without 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 tool with 5 optional parameters and no output schema, the description covers purpose, source selection, optional subdomain/PIN, and return value. It leaves error semantics (subdomain_taken) to the schema, which is acceptable, but a brief note on response shape beyond 'URL' would be more 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 already documents all five parameters (coverage 100%), so the baseline is 3. The description adds the mutual-exclusion rule across html_content/pdf_base64/files and clarifies that files are for text-only static sites, which is decision-relevant beyond the schema fields.

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 opens with a specific verb and resource: 'Публикует сайт на htmlkin.ru' and states the return value (public URL). Listing the three accepted source formats (html_content, pdf_base64, files) further defines the operation and distinguishes it from sibling delete/get/update tools.

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 explicitly says 'Принимает ровно один источник' (exactly one source), guiding parameter selection, and routes binary assets to ZIP via REST API or browser, an explicit alternative. It does not, however, contrast with htmlkin_update/delete, so sibling differentiation is incomplete.

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 burden and does so well. It discloses that the update always fully replaces the site, that html_content converts a multi-file site into a single-file site, that the address does not change, and that content type can be switched between HTML and PDF.

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 compact and every sentence adds information: the update scope, the replacement behavior, the address stability, the content-type switching, and the PIN-only case. It is front-loaded with the core purpose and avoids redundant boilerplate.

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 mutation tool with no annotations and no output schema, the description together with the schema fully covers what an agent needs to call it correctly: valid page identification, content constraints, replacement semantics, and the PIN-only variant. Nothing essential 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?

Even though the schema already documents all 5 parameters, the description adds crucial cross-parameter semantics: at most one of html_content, pdf_base64, or files may be provided, passing only pin changes protection, and html_content has a transformative effect on multi-file sites. This goes well beyond the individual field descriptions.

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 specific verb and resource: updates an already published site by its identifier. It clearly distinguishes itself from siblings by emphasizing 'previously published' and by explaining that the address stays the same, making it distinct from publish, delete, and get.

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 description clearly states the use case: updating an existing published site and optionally changing only the PIN. It implies the boundary against publish by saying 'previously published site,' but it does not explicitly name alternatives or say when not to use this tool.

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