crawlinx-mcp

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

Discloses that it diffs against the previous scan of the same domain automatically and outputs health movement and issue codes. However, it does not address what happens if no previous scan exists or any potential side effects, which is a gap given no 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?

Two sentences, first defining the action and output, second giving usage guidance. No unnecessary words, highly efficient.

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?

Covers purpose, usage, and output components. Lacks details on return format and error cases, but for a simple tool with one parameter and no output schema, it is mostly 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 coverage is 100% with a single parameter description. The tool description adds no additional parameter semantics beyond what the schema already explains, so baseline score of 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?

The description clearly states the verb (diff), resource (scan), and specifics (health movement plus issue codes of changes), distinguishing it from siblings like get_issue_detail and get_report.

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 recommends use when auditing in a loop to verify fixes and detect regressions, providing a clear scenario. Does not explicitly exclude other uses or mention alternatives, but the context is sufficient.

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 discloses key behaviors: returns affected URLs, step-by-step remediation, and mentions handling of false alarms. It does not detail side effects or safety, but the scope is well communicated.

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 concise sentences, first covering purpose and outputs, second providing usage context. No redundant 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 simple tool with 2 parameters and no output schema, the description fully answers what, when, and what to expect. No obvious gaps.

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 100%, so baseline is 3. The description adds usage context but no new parameter semantics beyond examples and field names already in 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 uses a specific verb 'Drill into' and resource 'issue code', lists outputs ('every affected URL plus step-by-step remediation'), and distinguishes from sibling by stating 'Call this after get_report_markdown to expand a code from the collapsed table'.

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 states to call after get_report_markdown and for the purpose of expanding a code before applying fixes. No exclusions or alternatives mentioned, but the sequential context is clear.

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?

Without annotations, the description carries full burden. It explains output format and contents, but does not disclose side effects (likely none, but not stated), prerequisites (scan must be finished), or error behavior. The statement 'finished report' implies state dependency, but this is not fully explicit.

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 with no wasted words. The first sentence hooks with the preferred usage, the second provides details. Information is front-loaded and efficient.

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 tool with one parameter and no output schema, the description adequately explains return values (health score, subscores, issues, stats). It mentions 'finished report', setting context. However, it does not cover error cases or handling of non-existent reports.

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% for the single parameter scan_id, so baseline is 3. The description does not add extra meaning beyond the schema's description ('the scan id returned by scan_url'). No additional format, constraints, or examples.

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 it fetches a finished report as structured JSON, listing specific contents (health score, category subscores, issues, stats). The verb 'fetch' and resource 'finished report' are precise. It distinguishes from sibling get_report_markdown by specifying JSON format and purpose (reasoning about what to fix).

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 explicitly positions this tool as 'PREFERRED for reasoning about what to fix' and instructs to use it when deciding which problems matter. However, it does not explicitly state when not to use it or mention alternatives beyond implicit contrast with sibling tools.

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 provided, so description bears full burden. It reveals that output is Markdown, compact by default, and includes a data format note. Yet, it omits handling of unfinished reports, error states, or potential side effects.

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 no redundancy. First sentence covers purpose and output format; second provides usage guidance and sibling reference. Information is front-loaded and efficient.

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?

The description is thorough for a tool without output schema: it details what the Markdown contains (health, fix plan, collapsed issues) and explains the full parameter. It also points to a sibling for further expansion. Lacks info on default behavior of domain or error handling.

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?

All three parameters are described in the schema (100% coverage). The description adds value by explaining the effect of full (compact vs large human report) and the purpose of scan_id (from scan_url). This enriches the schema definitions.

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 tool fetches a finished report as compact Markdown, specifying content: health, fix plan, collapsed issues. It distinguishes from sibling get_issue_detail by directing to use that for expanding individual 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?

The description advises when to use the compact view vs full (full=true) and references get_issue_detail for deeper detail. However, it does not explicitly compare to get_report or diff_scan, or state when not to use the 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?

Describes async behavior, crawl limits (max_pages, default/max), and that it returns a scan id. While no annotations exist, the description adequately conveys non-blocking nature and scope. Could mention if any destructive actions occur, but likely none.

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 purpose, then operational details. Every sentence serves a purpose; no fluff.

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?

Covers input, behavior, and output (scan id) with guidance on polling. No output schema, but description explains what to do next. Could briefly mention sibling tools for completeness, but not required.

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%, but description adds value: default values (max_pages=50, max=200), explanation of mode (free vs instant), and behavior for max_pages when mode=instant. Goes beyond 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?

Clearly states the tool submits a URL for an SEO audit, specifying the action (submit/audit), resource (URL), and outcome (scan id). Distinguishes from sibling tools like get_report which retrieve results.

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?

Provides clear usage context: submit URL, then poll get_report/get_report_markdown for results. However, does not explicitly state when not to use this tool versus alternatives like diff_scan.

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