Black Water Window Cleaning Website MCP

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

Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds that it returns content in Markdown or stripped text up to a 40,000-character limit, which is useful. However, it doesn't disclose what happens if the page exceeds the limit (truncation?), whether it follows redirects, or how it handles dynamic content (Cloudflare Markdown might imply some rendering). With openWorldHint=true, the domain restriction is clear, but the character limit is only partially explained.

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?

One sentence, front-loaded with the action and resource, then adds the format and limit. No wasted words. The sentence is concise and all information is relevant.

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 read tool with one parameter and no output schema, the description covers the action, the resource scope, output formats, and a size limit. It doesn't explain pagination or behavior on errors, but with annotations covering safety and idempotency, this is nearly complete. The only minor gap is the exact behavior when the page exceeds the character limit, which might be important for an agent deciding whether to use this over search.

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. The description clearly states that the 'url' parameter should be a page on the blackwaterwindowcleaning.com domain. It doesn't add format details (e.g., must be https), but the 'format: uri' in the schema covers that. The description does not explain the output options (Markdown vs stripped text), but that's not parameter semantics; the parameter is just the URL. For a single-parameter tool, a 4 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 ('Read'), a resource (the blackwaterwindowcleaning.com website page), and the output formats (Markdown or stripped text). The domain restriction is clear. It does not explicitly distinguish from siblings like search_pages, but 'read one page' is distinct from searching, so it's reasonably clear.

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 implies the tool is for reading individual pages on that domainhare, which helps when to use it. It doesn't name alternatives or explicit exclusions (e.g., when to use search_pages), but the context (a single URL input) makes usage fairly clear. Slight gap in not mentioning page size or dynamic content limitations.

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, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the behavioral detail of sitemap search and match score, which is useful. However, it does not disclose pagination behavior or the meaning of the match score, which would be valuable. Since annotations provide the basic safety traits, 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?

The description is two sentences with zero waste. It front-loads the key scoping detail (URL path search) and includes the output type. Every word earns its place, achieving ideal conciseness.

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?

This is a simple search tool with only 2 parameters and an output of URLs. Annotations cover safety and idempotency. The description explains the search mechanism adequately. Missing context includes the exact return format or scoring algorithm, but given the tool's simplicity and lack of output schema, this is a minor gap.

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 clarify parameter meanings. It explicitly states that the query searches words in URL path, giving meaning to the 'query' parameter. The 'limit' parameter is left to schema defaults, but the description's mention of 'Returns URLs with a match score' implies result ordering. This goes beyond the schema's bare minimum.

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 the verb ('Find'), the resource ('pages on blackwaterwindowcleaning.com'), the search method ('by words in their URL path'), and the output ('Returns URLs with a match score'). It also distinguishes itself from siblings by specifying sitemap-based URL path search rather than content 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?

The description implies when to use this tool (when searching pages by URL path keywords) but does not explicitly mention alternatives or when not to use it. The sibling names (read_page, site_info) hint at alternatives but are not referenced. Clear context is provided, but exclusion criteria are omitted.

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?

The annotations already establish readOnlyHint, openWorldHint, idempotentHint, and non-destructive behavior, so the description does not need to restate those. It adds output-scope detail about returning links to sitemap, docs, contact, and discovery documents, but no additional operational caveats such as rate limits or freshness. The description does not contradict the annotations.

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 one tight, front-loaded sentence that names the resource and then compactly enumerates the link categories it returns. There is no filler or redundancy with the title or schema.

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, heavily annotated read-only tool, this is mostly adequate: it explains the general topic and what links the result includes. The main gap is that it does not clarify how site_info relates to read_page and search_pages, which matters for choosing correctly among sibling tools.

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, confirmed by both the empty input schema and additionalProperties: false. With no parameters, there is no semantic burden for the description, and the schema completely defines the valid invocation.

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 identifies the target resource ('Black Water Window Cleaning (blackwaterwindowcleaning.com)') and the deliverable: an overview 'with links to its sitemap, docs, contact and every discovery document.' It is not a tautology, but it never explicitly contrasts with read_page or search_pages, 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?

There is no guidance about when to call site_info versus read_page or search_pages, and no exclusions or alternatives are named. The description only lists what the tool contains, leaving the agent to infer the intended entry-point role.

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